transformers/main/ja/model_doc/convbert.md

ConvBERT

Overview

ConvBERT モデルは、ConvBERT: Improving BERT with Span-based Dynamic Convolution で Zihang Jiang、Weihao Yu、Daquan Zhou、Yunpeng Chen、Jiashi Feng、Shuicheng Yan によって提案されました。 やん。

論文の要約は次のとおりです。

BERT やそのバリアントなどの事前トレーニング済み言語モデルは、最近、さまざまな環境で目覚ましいパフォーマンスを達成しています。 自然言語理解タスク。ただし、BERT はグローバルな自己注意ブロックに大きく依存しているため、問題が発生します。 メモリ使用量と計算コストが大きくなります。すべての注意が入力シーケンス全体に対してクエリを実行しますが、 グローバルな観点からアテンション マップを生成すると、一部のヘッドはローカルな依存関係のみを学習する必要があることがわかります。 これは、計算の冗長性が存在することを意味します。したがって、我々は、新しいスパンベースの動的畳み込みを提案します。 これらのセルフアテンション ヘッドを置き換えて、ローカルの依存関係を直接モデル化します。新しいコンボリューションヘッドと、 自己注意の頭を休め、グローバルとローカルの両方の状況でより効率的な新しい混合注意ブロックを形成します 学ぶ。この混合注意設計を BERT に装備し、ConvBERT モデルを構築します。実験でわかったことは、 ConvBERT は、トレーニング コストが低く、さまざまな下流タスクにおいて BERT およびその亜種よりも大幅に優れたパフォーマンスを発揮します。 モデルパラメータが少なくなります。注目すべきことに、ConvBERTbase モデルは 86.4 GLUE スコアを達成し、ELECTRAbase よりも 0.7 高いのに対し、 トレーニングコストは 1/4 未満です。コードと事前トレーニングされたモデルがリリースされます。

このモデルは、abhishek によって提供されました。オリジナルの実装が見つかります ここ: https://github.com/yitu-opensource/ConvBert

Usage tips

ConvBERT トレーニングのヒントは BERT のヒントと似ています。使用上のヒントについては、BERT ドキュメント を参照してください。

Resources

• テキスト分類タスクガイド(英語版)
• トークン分類タスクガイド
• 質問回答タスク ガイド
• マスクされた言語モデリング タスク ガイド
• 多肢選択タスク ガイド

ConvBertConfig[[transformers.ConvBertConfig]]

transformers.ConvBertConfig[[transformers.ConvBertConfig]]

Source

This is the configuration class to store the configuration of a ConvBertModel. It is used to instantiate a Convbert 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 YituTech/conv-bert-base

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

Example:

>>> from transformers import ConvBertConfig, ConvBertModel

>>> # Initializing a ConvBERT convbert-base-uncased style configuration
>>> configuration = ConvBertConfig()

>>> # Initializing a model (with random weights) from the convbert-base-uncased style configuration
>>> model = ConvBertModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

Parameters:

vocab_size (int, optional, defaults to 30522) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the input_ids.

hidden_size (int, optional, defaults to 768) : Dimension of the hidden representations.

num_hidden_layers (int, optional, defaults to 12) : Number of hidden layers in the Transformer decoder.

num_attention_heads (int, optional, defaults to 12) : Number of attention heads for each attention layer in the Transformer decoder.

intermediate_size (int, optional, defaults to 3072) : Dimension of the MLP representations.

hidden_act (str, optional, defaults to gelu) : The non-linear activation function (function or string) in the decoder. For example, "gelu", "relu", "silu", etc.

hidden_dropout_prob (Union[float, int], optional, defaults to 0.1) : The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

attention_probs_dropout_prob (Union[float, int], optional, defaults to 0.1) : 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.

type_vocab_size (int, optional, defaults to 2) : The vocabulary size of the token_type_ids.

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.

pad_token_id (int, optional, defaults to 1) : Token id used for padding in the vocabulary.

bos_token_id (int, optional, defaults to 0) : Token id used for beginning-of-stream in the vocabulary.

eos_token_id (Union[int, list[int]], optional, defaults to 2) : Token id used for end-of-stream in the vocabulary.

embedding_size (int, optional, defaults to 768) : Dimensionality of the embeddings and hidden states.

head_ratio (int, optional, defaults to 2) : Ratio gamma to reduce the number of attention heads.

conv_kernel_size (int, optional, defaults to 9) : The size of the convolutional kernel.

num_groups (int, optional, defaults to 1) : The number of groups for grouped linear layers for ConvBert model

classifier_dropout (Union[float, int], optional) : The dropout ratio for classifier.

is_decoder (bool, optional, defaults to False) : Whether the model is used as a decoder or not. If False, the model is used as an encoder.

add_cross_attention (bool, optional, defaults to False) : Whether cross-attention layers should be added to the model.

tie_word_embeddings (bool, optional, defaults to True) : Whether to tie weight embeddings according to model's tied_weights_keys mapping.

ConvBertTokenizer[[transformers.ConvBertTokenizer]]

transformers.ConvBertTokenizer[[transformers.ConvBertTokenizer]]

Source

Construct a ConvBERT tokenizer (backed by HuggingFace's tokenizers library). Based on WordPiece.

This tokenizer inherits from BertTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

get_special_tokens_masktransformers.ConvBertTokenizer.get_special_tokens_maskhttps://github.com/huggingface/transformers/blob/main/src/transformers/tokenization_utils_base.py#L1318[{"name": "token_ids_0", "val": ": list[int]"}, {"name": "token_ids_1", "val": ": list[int] | None = None"}, {"name": "already_has_special_tokens", "val": ": bool = False"}]- token_ids_0 -- List of IDs for the (possibly already formatted) sequence.

• token_ids_1 -- Unused when already_has_special_tokens=True. Must be None in that case.
• already_has_special_tokens -- Whether the sequence is already formatted with special tokens.0A list of integers in the range [0, 1]1 for a special token, 0 for a sequence token.

Retrieve sequence ids from a token list that has no special tokens added.

For fast tokenizers, data collators call this with already_has_special_tokens=True to build a mask over an already-formatted sequence. In that case, we compute the mask by checking membership in all_special_ids.

Parameters:

token_ids_0 : List of IDs for the (possibly already formatted) sequence.

token_ids_1 : Unused when already_has_special_tokens=True. Must be None in that case.

already_has_special_tokens : Whether the sequence is already formatted with special tokens.

Returns:

A list of integers in the range [0, 1]

1 for a special token, 0 for a sequence token.

save_vocabulary[[transformers.ConvBertTokenizer.save_vocabulary]]

Source

ConvBertTokenizerFast[[transformers.ConvBertTokenizer]]

transformers.ConvBertTokenizer[[transformers.ConvBertTokenizer]]

Source

Construct a ConvBERT tokenizer (backed by HuggingFace's tokenizers library). Based on WordPiece.

This tokenizer inherits from BertTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

ConvBertModel[[transformers.ConvBertModel]]

transformers.ConvBertModel[[transformers.ConvBertModel]]

Source

The bare Convbert Model outputting raw hidden-states without any specific head on top.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forwardtransformers.ConvBertModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/convbert/modeling_convbert.py#L599[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) -- Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

  What are attention masks?

• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:

  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.

  What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].

  What are position IDs?

• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) -- Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.0BaseModelOutputWithCrossAttentions or tuple(torch.FloatTensor)A BaseModelOutputWithCrossAttentions or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs. The ConvBertModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

• last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)) -- Sequence of hidden-states at the output of the last layer of the model.

• hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) -- Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

• attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) -- Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

• cross_attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True and config.add_cross_attention=True is passed or when config.output_attentions=True) -- Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

Parameters:

config (ConvBertModel) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Returns:

[BaseModelOutputWithCrossAttentions](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithCrossAttentions) or tuple(torch.FloatTensor)``

A BaseModelOutputWithCrossAttentions or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs.

ConvBertForMaskedLM[[transformers.ConvBertForMaskedLM]]

transformers.ConvBertForMaskedLM[[transformers.ConvBertForMaskedLM]]

Source

The Convbert Model with a language modeling head on top."

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forwardtransformers.ConvBertForMaskedLM.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/convbert/modeling_convbert.py#L694[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) -- Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

  What are attention masks?

• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:

  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.

  What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].

  What are position IDs?

• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) -- Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

• labels (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Labels for computing the masked language modeling loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]0MaskedLMOutput or tuple(torch.FloatTensor)A MaskedLMOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs. The ConvBertForMaskedLM forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) -- Masked language modeling (MLM) loss.

• logits (torch.FloatTensor of shape (batch_size, sequence_length, config.vocab_size)) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

• hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) -- Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

• attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) -- Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Example:

>>> from transformers import AutoTokenizer, ConvBertForMaskedLM
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("YituTech/conv-bert-base")
>>> model = ConvBertForMaskedLM.from_pretrained("YituTech/conv-bert-base")

>>> inputs = tokenizer("The capital of France is .", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> # retrieve index of 
>>> mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]

>>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)
>>> tokenizer.decode(predicted_token_id)
...

>>> labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"]
>>> # mask labels of non- tokens
>>> labels = torch.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100)

>>> outputs = model(**inputs, labels=labels)
>>> round(outputs.loss.item(), 2)
...

Parameters:

config (ConvBertForMaskedLM) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Returns:

[MaskedLMOutput](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or tuple(torch.FloatTensor)``

A MaskedLMOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs.

ConvBertForSequenceClassification[[transformers.ConvBertForSequenceClassification]]

transformers.ConvBertForSequenceClassification[[transformers.ConvBertForSequenceClassification]]

Source

ConvBERT Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forwardtransformers.ConvBertForSequenceClassification.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/convbert/modeling_convbert.py#L780[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) -- Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

  What are attention masks?

• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:

  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.

  What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].

  What are position IDs?

• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) -- Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

• labels (torch.LongTensor of shape (batch_size,), optional) -- Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).0SequenceClassifierOutput or tuple(torch.FloatTensor)A SequenceClassifierOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs. The ConvBertForSequenceClassification forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) -- Classification (or regression if config.num_labels==1) loss.

• logits (torch.FloatTensor of shape (batch_size, config.num_labels)) -- Classification (or regression if config.num_labels==1) scores (before SoftMax).

• hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) -- Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

• attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) -- Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Example of single-label classification:

>>> import torch
>>> from transformers import AutoTokenizer, ConvBertForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("YituTech/conv-bert-base")
>>> model = ConvBertForSequenceClassification.from_pretrained("YituTech/conv-bert-base")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_id = logits.argmax().item()
>>> model.config.id2label[predicted_class_id]
...

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = ConvBertForSequenceClassification.from_pretrained("YituTech/conv-bert-base", num_labels=num_labels)

>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
...

Example of multi-label classification:

>>> import torch
>>> from transformers import AutoTokenizer, ConvBertForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("YituTech/conv-bert-base")
>>> model = ConvBertForSequenceClassification.from_pretrained("YituTech/conv-bert-base", problem_type="multi_label_classification")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = ConvBertForSequenceClassification.from_pretrained(
...     "YituTech/conv-bert-base", num_labels=num_labels, problem_type="multi_label_classification"
... )

>>> labels = torch.sum(
...     torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).loss

Parameters:

config (ConvBertForSequenceClassification) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Returns:

[SequenceClassifierOutput](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or tuple(torch.FloatTensor)``

A SequenceClassifierOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs.

ConvBertForMultipleChoice[[transformers.ConvBertForMultipleChoice]]

transformers.ConvBertForMultipleChoice[[transformers.ConvBertForMultipleChoice]]

Source

The Convbert Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forwardtransformers.ConvBertForMultipleChoice.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/convbert/modeling_convbert.py#L853[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- input_ids (torch.LongTensor of shape (batch_size, num_choices, sequence_length)) -- Indices of input sequence tokens in the vocabulary.

Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) -- Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

  What are attention masks?

• token_type_ids (torch.LongTensor of shape (batch_size, num_choices, sequence_length), optional) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:

  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.

  What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, num_choices, sequence_length), optional) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

  What are position IDs?

• inputs_embeds (torch.FloatTensor of shape (batch_size, num_choices, sequence_length, hidden_size), optional) -- Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

• labels (torch.LongTensor of shape (batch_size,), optional) -- Labels for computing the multiple choice classification loss. Indices should be in [0, ..., num_choices-1] where num_choices is the size of the second dimension of the input tensors. (See input_ids above)0MultipleChoiceModelOutput or tuple(torch.FloatTensor)A MultipleChoiceModelOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs. The ConvBertForMultipleChoice forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) -- Classification loss.

• logits (torch.FloatTensor of shape (batch_size, num_choices)) -- num_choices is the second dimension of the input tensors. (see input_ids above).

  Classification scores (before SoftMax).

• hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) -- Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

• attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) -- Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Example:

>>> from transformers import AutoTokenizer, ConvBertForMultipleChoice
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("YituTech/conv-bert-base")
>>> model = ConvBertForMultipleChoice.from_pretrained("YituTech/conv-bert-base")

>>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced."
>>> choice0 = "It is eaten with a fork and a knife."
>>> choice1 = "It is eaten while held in the hand."
>>> labels = torch.tensor(0).unsqueeze(0)  # choice0 is correct (according to Wikipedia ;)), batch size 1

>>> encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors="pt", padding=True)
>>> outputs = model(**{k: v.unsqueeze(0) for k, v in encoding.items()}, labels=labels)  # batch size is 1

>>> # the linear classifier still needs to be trained
>>> loss = outputs.loss
>>> logits = outputs.logits

Parameters:

config (ConvBertForMultipleChoice) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Returns:

[MultipleChoiceModelOutput](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or tuple(torch.FloatTensor)``

A MultipleChoiceModelOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs.

ConvBertForTokenClassification[[transformers.ConvBertForTokenClassification]]

transformers.ConvBertForTokenClassification[[transformers.ConvBertForTokenClassification]]

Source

The Convbert transformer with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forwardtransformers.ConvBertForTokenClassification.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/convbert/modeling_convbert.py#L952[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) -- Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

  What are attention masks?

• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:

  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.

  What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].

  What are position IDs?

• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) -- Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

• labels (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Labels for computing the token classification loss. Indices should be in [0, ..., config.num_labels - 1].0TokenClassifierOutput or tuple(torch.FloatTensor)A TokenClassifierOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs. The ConvBertForTokenClassification forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) -- Classification loss.

• logits (torch.FloatTensor of shape (batch_size, sequence_length, config.num_labels)) -- Classification scores (before SoftMax).

• hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) -- Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

• attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) -- Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Example:

>>> from transformers import AutoTokenizer, ConvBertForTokenClassification
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("YituTech/conv-bert-base")
>>> model = ConvBertForTokenClassification.from_pretrained("YituTech/conv-bert-base")

>>> inputs = tokenizer(
...     "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt"
... )

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_token_class_ids = logits.argmax(-1)

>>> # Note that tokens are classified rather then input words which means that
>>> # there might be more predicted token classes than words.
>>> # Multiple token classes might account for the same word
>>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
>>> predicted_tokens_classes
...

>>> labels = predicted_token_class_ids
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
...

Parameters:

config (ConvBertForTokenClassification) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Returns:

[TokenClassifierOutput](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or tuple(torch.FloatTensor)``

A TokenClassifierOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs.

ConvBertForQuestionAnswering[[transformers.ConvBertForQuestionAnswering]]

transformers.ConvBertForQuestionAnswering[[transformers.ConvBertForQuestionAnswering]]

Source

The Convbert transformer with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layer on top of the hidden-states output to compute span start logits and span end logits).

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forwardtransformers.ConvBertForQuestionAnswering.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/convbert/modeling_convbert.py#L1007[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "start_positions", "val": ": torch.LongTensor | None = None"}, {"name": "end_positions", "val": ": torch.LongTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) -- Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

  What are attention masks?

• token_type_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:

  • 0 corresponds to a sentence A token,
  • 1 corresponds to a sentence B token.

  What are token type IDs?

• position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].

  What are position IDs?

• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) -- Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

• start_positions (torch.LongTensor of shape (batch_size,), optional) -- Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.

• end_positions (torch.LongTensor of shape (batch_size,), optional) -- Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.0QuestionAnsweringModelOutput or tuple(torch.FloatTensor)A QuestionAnsweringModelOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs. The ConvBertForQuestionAnswering forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) -- Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.

• start_logits (torch.FloatTensor of shape (batch_size, sequence_length)) -- Span-start scores (before SoftMax).

• end_logits (torch.FloatTensor of shape (batch_size, sequence_length)) -- Span-end scores (before SoftMax).

• hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) -- Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

• attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) -- Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Example:

>>> from transformers import AutoTokenizer, ConvBertForQuestionAnswering
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("YituTech/conv-bert-base")
>>> model = ConvBertForQuestionAnswering.from_pretrained("YituTech/conv-bert-base")

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"

>>> inputs = tokenizer(question, text, return_tensors="pt")
>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> answer_start_index = outputs.start_logits.argmax()
>>> answer_end_index = outputs.end_logits.argmax()

>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
>>> tokenizer.decode(predict_answer_tokens, skip_special_tokens=True)
...

>>> # target is "nice puppet"
>>> target_start_index = torch.tensor([14])
>>> target_end_index = torch.tensor([15])

>>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
>>> loss = outputs.loss
>>> round(loss.item(), 2)
...

Parameters:

config (ConvBertForQuestionAnswering) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Returns:

[QuestionAnsweringModelOutput](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) or tuple(torch.FloatTensor)``

A QuestionAnsweringModelOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (ConvBertConfig) and inputs.