# coding=utf-8 # Copyright 2018 The Google AI Language Team Authors and 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. """ ALBERT model configuration""" from collections import OrderedDict from typing import Mapping from ...configuration_utils import PretrainedConfig from ...onnx import OnnxConfig ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = { "albert-base-v1": "https://huggingface.co/albert-base-v1/resolve/main/config.json", "albert-large-v1": "https://huggingface.co/albert-large-v1/resolve/main/config.json", "albert-xlarge-v1": "https://huggingface.co/albert-xlarge-v1/resolve/main/config.json", "albert-xxlarge-v1": "https://huggingface.co/albert-xxlarge-v1/resolve/main/config.json", "albert-base-v2": "https://huggingface.co/albert-base-v2/resolve/main/config.json", "albert-large-v2": "https://huggingface.co/albert-large-v2/resolve/main/config.json", "albert-xlarge-v2": "https://huggingface.co/albert-xlarge-v2/resolve/main/config.json", "albert-xxlarge-v2": "https://huggingface.co/albert-xxlarge-v2/resolve/main/config.json", } class AlbertConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`AlbertModel`] or a [`TFAlbertModel`]. It is used to instantiate an ALBERT 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 ALBERT [albert-xxlarge-v2](https://huggingface.co/albert-xxlarge-v2) 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 30000): Vocabulary size of the ALBERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`AlbertModel`] or [`TFAlbertModel`]. embedding_size (`int`, *optional*, defaults to 128): Dimensionality of vocabulary embeddings. hidden_size (`int`, *optional*, defaults to 4096): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_hidden_groups (`int`, *optional*, defaults to 1): Number of groups for the hidden layers, parameters in the same group are shared. num_attention_heads (`int`, *optional*, defaults to 64): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 16384): The dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. inner_group_num (`int`, *optional*, defaults to 1): The number of inner repetition of attention and ffn. hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu_new"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0): The dropout ratio for the attention probabilities. max_position_embeddings (`int`, *optional*, defaults to 512): The maximum sequence length that this model might ever be used with. Typically set this to something large (e.g., 512 or 1024 or 2048). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`AlbertModel`] or [`TFAlbertModel`]. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. classifier_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for attached classifiers. position_embedding_type (`str`, *optional*, defaults to `"absolute"`): Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"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). pad_token_id (`int`, *optional*, defaults to 0): Padding token id. bos_token_id (`int`, *optional*, defaults to 2): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 3): End of stream token id. Examples: ```python >>> from transformers import AlbertConfig, AlbertModel >>> # Initializing an ALBERT-xxlarge style configuration >>> albert_xxlarge_configuration = AlbertConfig() >>> # Initializing an ALBERT-base style configuration >>> albert_base_configuration = AlbertConfig( ... hidden_size=768, ... num_attention_heads=12, ... intermediate_size=3072, ... ) >>> # Initializing a model (with random weights) from the ALBERT-base style configuration >>> model = AlbertModel(albert_xxlarge_configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "albert" def __init__( self, vocab_size=30000, embedding_size=128, hidden_size=4096, num_hidden_layers=12, num_hidden_groups=1, num_attention_heads=64, intermediate_size=16384, inner_group_num=1, hidden_act="gelu_new", hidden_dropout_prob=0, attention_probs_dropout_prob=0, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, classifier_dropout_prob=0.1, position_embedding_type="absolute", pad_token_id=0, bos_token_id=2, eos_token_id=3, **kwargs, ): super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs) self.vocab_size = vocab_size self.embedding_size = embedding_size self.hidden_size = hidden_size self.num_hidden_layers = num_hidden_layers self.num_hidden_groups = num_hidden_groups self.num_attention_heads = num_attention_heads self.inner_group_num = inner_group_num 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.classifier_dropout_prob = classifier_dropout_prob self.position_embedding_type = position_embedding_type # Copied from transformers.models.bert.configuration_bert.BertOnnxConfig with Roberta->Albert class AlbertOnnxConfig(OnnxConfig): @property def inputs(self) -> Mapping[str, Mapping[int, str]]: if self.task == "multiple-choice": dynamic_axis = {0: "batch", 1: "choice", 2: "sequence"} else: dynamic_axis = {0: "batch", 1: "sequence"} return OrderedDict( [ ("input_ids", dynamic_axis), ("attention_mask", dynamic_axis), ("token_type_ids", dynamic_axis), ] )