FlauBERT¶

Overview¶

The FlauBERT model was proposed in the paper FlauBERT: Unsupervised Language Model Pre-training for French by Hang Le et al. It’s a transformer model pretrained using a masked language modeling (MLM) objective (like BERT).

The abstract from the paper is the following:

Language models have become a key step to achieve state-of-the art results in many different Natural Language Processing (NLP) tasks. Leveraging the huge amount of unlabeled texts nowadays available, they provide an efficient way to pre-train continuous word representations that can be fine-tuned for a downstream task, along with their contextualization at the sentence level. This has been widely demonstrated for English using contextualized representations (Dai and Le, 2015; Peters et al., 2018; Howard and Ruder, 2018; Radford et al., 2018; Devlin et al., 2019; Yang et al., 2019b). In this paper, we introduce and share FlauBERT, a model learned on a very large and heterogeneous French corpus. Models of different sizes are trained using the new CNRS (French National Centre for Scientific Research) Jean Zay supercomputer. We apply our French language models to diverse NLP tasks (text classification, paraphrasing, natural language inference, parsing, word sense disambiguation) and show that most of the time they outperform other pretraining approaches. Different versions of FlauBERT as well as a unified evaluation protocol for the downstream tasks, called FLUE (French Language Understanding Evaluation), are shared to the research community for further reproducible experiments in French NLP.

This model was contributed by formiel. The original code can be found here.

FlaubertConfig¶

class transformers.FlaubertConfig(layerdrop=0.0, pre_norm=False, pad_token_id=2, bos_token_id=0, **kwargs)[source]¶

This is the configuration class to store the configuration of a FlaubertModel or a TFFlaubertModel. It is used to instantiate a FlauBERT model according to the specified arguments, defining the model architecture.

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

Parameters

pre_norm (bool, optional, defaults to False) – Whether to apply the layer normalization before or after the feed forward layer following the attention in each layer (Vaswani et al., Tensor2Tensor for Neural Machine Translation. 2018)
layerdrop (float, optional, defaults to 0.0) – Probability to drop layers during training (Fan et al., Reducing Transformer Depth on Demand with Structured Dropout. ICLR 2020)
vocab_size (int, optional, defaults to 30145) – Vocabulary size of the FlauBERT model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling FlaubertModel or TFFlaubertModel.
emb_dim (int, optional, defaults to 2048) – Dimensionality of the encoder layers and the pooler layer.
n_layer (int, optional, defaults to 12) – Number of hidden layers in the Transformer encoder.
n_head (int, optional, defaults to 16) – Number of attention heads for each attention layer in the Transformer encoder.
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 0.1) – The dropout probability for the attention mechanism
gelu_activation (bool, optional, defaults to True) – Whether or not to use a gelu activation instead of relu.
sinusoidal_embeddings (bool, optional, defaults to False) – Whether or not to use sinusoidal positional embeddings instead of absolute positional embeddings.
causal (bool, optional, defaults to False) – Whether or not the model should behave in a causal manner. Causal models use a triangular attention mask in order to only attend to the left-side context instead if a bidirectional context.
asm (bool, optional, defaults to False) – Whether or not to use an adaptive log softmax projection layer instead of a linear layer for the prediction layer.
n_langs (int, optional, defaults to 1) – The number of languages the model handles. Set to 1 for monolingual models.
use_lang_emb (bool, optional, defaults to True) – Whether to use language embeddings. Some models use additional language embeddings, see the multilingual models page for information on how to use them.
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 just in case (e.g., 512 or 1024 or 2048).
embed_init_std (float, optional, defaults to 2048^-0.5) – The standard deviation of the truncated_normal_initializer for initializing the embedding matrices.
init_std (int, optional, defaults to 50257) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices except the embedding matrices.
layer_norm_eps (float, optional, defaults to 1e-12) – The epsilon used by the layer normalization layers.
bos_index (int, optional, defaults to 0) – The index of the beginning of sentence token in the vocabulary.
eos_index (int, optional, defaults to 1) – The index of the end of sentence token in the vocabulary.
pad_index (int, optional, defaults to 2) – The index of the padding token in the vocabulary.
unk_index (int, optional, defaults to 3) – The index of the unknown token in the vocabulary.
mask_index (int, optional, defaults to 5) – The index of the masking token in the vocabulary.
is_encoder (bool, optional, defaults to True) – Whether or not the initialized model should be a transformer encoder or decoder as seen in Vaswani et al.
summary_type (string, optional, defaults to “first”) –
Argument used when doing sequence summary. Used in the sequence classification and multiple choice models.

Has to be one of the following options:
- "last": Take the last token hidden state (like XLNet).
- "first": Take the first token hidden state (like BERT).
- "mean": Take the mean of all tokens hidden states.
- "cls_index": Supply a Tensor of classification token position (like GPT/GPT-2).
- "attn": Not implemented now, use multi-head attention.
summary_use_proj (bool, optional, defaults to True) –
Argument used when doing sequence summary. Used in the sequence classification and multiple choice models.

Whether or not to add a projection after the vector extraction.
summary_activation (str, optional) –
Argument used when doing sequence summary. Used in the sequence classification and multiple choice models.

Pass "tanh" for a tanh activation to the output, any other value will result in no activation.
summary_proj_to_labels (bool, optional, defaults to True) –
Used in the sequence classification and multiple choice models.

Whether the projection outputs should have config.num_labels or config.hidden_size classes.
summary_first_dropout (float, optional, defaults to 0.1) –
Used in the sequence classification and multiple choice models.

The dropout ratio to be used after the projection and activation.
start_n_top (int, optional, defaults to 5) – Used in the SQuAD evaluation script.
end_n_top (int, optional, defaults to 5) – Used in the SQuAD evaluation script.
mask_token_id (int, optional, defaults to 0) – Model agnostic parameter to identify masked tokens when generating text in an MLM context.
lang_id (int, optional, defaults to 1) – The ID of the language used by the model. This parameter is used when generating text in a given language.

FlaubertTokenizer¶

class transformers.FlaubertTokenizer(do_lowercase=False, **kwargs)[source]¶

Construct a Flaubert tokenizer. Based on Byte-Pair Encoding. The tokenization process is the following:

Moses preprocessing and tokenization.
Normalizing all inputs text.
The arguments special_tokens and the function set_special_tokens, can be used to add additional symbols (like “__classify__”) to a vocabulary.
The argument do_lowercase controls lower casing (automatically set for pretrained vocabularies).

This tokenizer inherits from XLMTokenizer. Please check the superclass for usage examples and documentation regarding arguments.

FlaubertModel¶

class transformers.FlaubertModel(config)[source]¶

The bare Flaubert Model transformer 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.

Parameters: config (FlaubertConfig) – 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.

forward(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

The FlaubertModel forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using FlaubertTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.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.max_position_embeddings - 1].

What are position IDs?
lengths (torch.LongTensor of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)]:
cache (Dict[str, torch.FloatTensor], optional) – Dictionary strings to torch.FloatTensor that contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding. The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

Returns

A BaseModelOutput 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 (FlaubertConfig) and inputs.

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 + 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 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.

Return type

BaseModelOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import FlaubertTokenizer, FlaubertModel
>>> import torch

>>> tokenizer = FlaubertTokenizer.from_pretrained('flaubert/flaubert_base_cased')
>>> model = FlaubertModel.from_pretrained('flaubert/flaubert_base_cased')

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

>>> last_hidden_states = outputs.last_hidden_state

FlaubertWithLMHeadModel¶

class transformers.FlaubertWithLMHeadModel(config)[source]¶

The Flaubert Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).

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.

Parameters: config (FlaubertConfig) – 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.

This class overrides XLMWithLMHeadModel. Please check the superclass for the appropriate documentation alongside usage examples.

forward(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)¶

The XLMWithLMHeadModel forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using XLMTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.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?
langs (torch.LongTensor of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
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.max_position_embeddings - 1].

What are position IDs?
lengths (torch.LongTensor of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, torch.FloatTensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.
labels (torch.LongTensor of shape (batch_size, sequence_length), optional) – Labels for language modeling. Note that the labels are shifted inside the model, i.e. you can set labels = input_ids Indices are selected in [-100, 0, ..., config.vocab_size] All labels set to -100 are ignored (masked), the loss is only computed for labels in [0, ..., config.vocab_size]

Returns

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 (XLMConfig) and inputs.

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 + 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 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.

Return type

MaskedLMOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import XLMTokenizer, XLMWithLMHeadModel
>>> import torch

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = XLMWithLMHeadModel.from_pretrained('xlm-mlm-en-2048')

>>> inputs = tokenizer("The capital of France is <special1>.", return_tensors="pt")
>>> labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"]

>>> outputs = model(**inputs, labels=labels)
>>> loss = outputs.loss
>>> logits = outputs.logits

FlaubertForSequenceClassification¶

class transformers.FlaubertForSequenceClassification(config)[source]¶

Flaubert Model 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.

Parameters: config (FlaubertConfig) – 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.

This class overrides XLMForSequenceClassification. Please check the superclass for the appropriate documentation alongside usage examples.

forward(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)¶

The XLMForSequenceClassification forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using XLMTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.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?
langs (torch.LongTensor of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
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.max_position_embeddings - 1].

What are position IDs?
lengths (torch.LongTensor of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, torch.FloatTensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.
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).

Returns

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 (XLMConfig) and inputs.

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 + 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 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.

Return type

SequenceClassifierOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import XLMTokenizer, XLMForSequenceClassification
>>> import torch

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = XLMForSequenceClassification.from_pretrained('xlm-mlm-en-2048')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1
>>> outputs = model(**inputs, labels=labels)
>>> loss = outputs.loss
>>> logits = outputs.logits

FlaubertForMultipleChoice¶

class transformers.FlaubertForMultipleChoice(config)[source]¶

Flaubert 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.

Parameters: config (FlaubertConfig) – 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.

This class overrides XLMForMultipleChoice. Please check the superclass for the appropriate documentation alongside usage examples.

forward(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)¶

The XLMForMultipleChoice forward method, overrides the __call__() special method.

Note

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.

Parameters

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 XLMTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

What are input IDs?
attention_mask (torch.FloatTensor of shape (batch_size, num_choices, 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?
langs (torch.LongTensor of shape (batch_size, num_choices, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
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?
lengths (torch.LongTensor of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, torch.FloatTensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.
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)

Returns

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 (XLMConfig) and inputs.

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 + 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 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.

Return type

MultipleChoiceModelOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import XLMTokenizer, XLMForMultipleChoice
>>> import torch

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = XLMForMultipleChoice.from_pretrained('xlm-mlm-en-2048')

>>> 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

FlaubertForTokenClassification¶

class transformers.FlaubertForTokenClassification(config)[source]¶

Flaubert Model 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.

Parameters: config (FlaubertConfig) – 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.

This class overrides XLMForTokenClassification. Please check the superclass for the appropriate documentation alongside usage examples.

forward(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)¶

The XLMForTokenClassification forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using XLMTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.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?
langs (torch.LongTensor of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
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.max_position_embeddings - 1].

What are position IDs?
lengths (torch.LongTensor of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, torch.FloatTensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.
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].

Returns

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 (XLMConfig) and inputs.

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 + 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 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.

Return type

TokenClassifierOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import XLMTokenizer, XLMForTokenClassification
>>> import torch

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = XLMForTokenClassification.from_pretrained('xlm-mlm-en-2048')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> labels = torch.tensor([1] * inputs["input_ids"].size(1)).unsqueeze(0)  # Batch size 1

>>> outputs = model(**inputs, labels=labels)
>>> loss = outputs.loss
>>> logits = outputs.logits

FlaubertForQuestionAnsweringSimple¶

class transformers.FlaubertForQuestionAnsweringSimple(config)[source]¶

Flaubert Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers 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.

Parameters: config (FlaubertConfig) – 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.

This class overrides XLMForQuestionAnsweringSimple. Please check the superclass for the appropriate documentation alongside usage examples.

forward(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, start_positions=None, end_positions=None, output_attentions=None, output_hidden_states=None, return_dict=None)¶

The XLMForQuestionAnsweringSimple forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using XLMTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.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?
langs (torch.LongTensor of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
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.max_position_embeddings - 1].

What are position IDs?
lengths (torch.LongTensor of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, torch.FloatTensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.
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.

Returns

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 (XLMConfig) and inputs.

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 + 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 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.

Return type

QuestionAnsweringModelOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import XLMTokenizer, XLMForQuestionAnsweringSimple
>>> import torch

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = XLMForQuestionAnsweringSimple.from_pretrained('xlm-mlm-en-2048')

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
>>> inputs = tokenizer(question, text, return_tensors='pt')
>>> start_positions = torch.tensor([1])
>>> end_positions = torch.tensor([3])

>>> outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions)
>>> loss = outputs.loss
>>> start_scores = outputs.start_logits
>>> end_scores = outputs.end_logits

FlaubertForQuestionAnswering¶

class transformers.FlaubertForQuestionAnswering(config)[source]¶

Flaubert Model with a beam-search span classification head on top for extractive question-answering tasks like SQuAD (a linear layers 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.

Parameters: config (FlaubertConfig) – 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.

This class overrides XLMForQuestionAnswering. Please check the superclass for the appropriate documentation alongside usage examples.

forward(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, start_positions=None, end_positions=None, is_impossible=None, cls_index=None, p_mask=None, output_attentions=None, output_hidden_states=None, return_dict=None)¶

The XLMForQuestionAnswering forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using XLMTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.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?
langs (torch.LongTensor of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
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.max_position_embeddings - 1].

What are position IDs?
lengths (torch.LongTensor of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, torch.FloatTensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.
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.
is_impossible (torch.LongTensor of shape (batch_size,), optional) – Labels whether a question has an answer or no answer (SQuAD 2.0)
cls_index (torch.LongTensor of shape (batch_size,), optional) – Labels for position (index) of the classification token to use as input for computing plausibility of the answer.
p_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) – Optional mask of tokens which can’t be in answers (e.g. [CLS], [PAD], …). 1.0 means token should be masked. 0.0 mean token is not masked.

Returns

A XLMForQuestionAnsweringOutput 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 (XLMConfig) and inputs.

loss (torch.FloatTensor of shape (1,), optional, returned if both start_positions and end_positions are provided) – Classification loss as the sum of start token, end token (and is_impossible if provided) classification losses.
start_top_log_probs (torch.FloatTensor of shape (batch_size, config.start_n_top), optional, returned if start_positions or end_positions is not provided) – Log probabilities for the top config.start_n_top start token possibilities (beam-search).
start_top_index (torch.LongTensor of shape (batch_size, config.start_n_top), optional, returned if start_positions or end_positions is not provided) – Indices for the top config.start_n_top start token possibilities (beam-search).
end_top_log_probs (torch.FloatTensor of shape (batch_size, config.start_n_top * config.end_n_top), optional, returned if start_positions or end_positions is not provided) – Log probabilities for the top config.start_n_top * config.end_n_top end token possibilities (beam-search).
end_top_index (torch.LongTensor of shape (batch_size, config.start_n_top * config.end_n_top), optional, returned if start_positions or end_positions is not provided) – Indices for the top config.start_n_top * config.end_n_top end token possibilities (beam-search).
cls_logits (torch.FloatTensor of shape (batch_size,), optional, returned if start_positions or end_positions is not provided) – Log probabilities for the is_impossible label of the answers.
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 + 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 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 XLMTokenizer, XLMForQuestionAnswering
>>> import torch

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = XLMForQuestionAnswering.from_pretrained('xlm-mlm-en-2048')

>>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)  # Batch size 1
>>> start_positions = torch.tensor([1])
>>> end_positions = torch.tensor([3])

>>> outputs = model(input_ids, start_positions=start_positions, end_positions=end_positions)
>>> loss = outputs.loss

Return type

XLMForQuestionAnsweringOutput or tuple(torch.FloatTensor)

TFFlaubertModel¶

class transformers.TFFlaubertModel(*args, **kwargs)[source]¶

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

This model inherits from TFPreTrainedModel. 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 tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

a single Tensor with input_ids only and nothing else: model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Parameters: config (FlaubertConfig) – 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.

call(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, training=False, **kwargs)[source]¶

The TFFlaubertModel forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using FlaubertTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

What are input IDs?
attention_mask (Numpy array or tf.Tensor 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?
langs (tf.Tensor or Numpy array of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
token_type_ids (tf.Tensor or Numpy array 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 (tf.Tensor or Numpy array 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.max_position_embeddings - 1].

What are position IDs?
lengths (tf.Tensor or Numpy array of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility Indices selected in [0, ..., input_ids.size(-1)]:
cache (Dict[str, tf.Tensor], optional) –
Dictionary string to tf.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
inputs_embeds (tf.Tensor 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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

Returns

A TFBaseModelOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (FlaubertConfig) and inputs.

last_hidden_state (tf.Tensor 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(tf.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + 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 initial embedding outputs.
attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Return type

TFBaseModelOutput or tuple(tf.Tensor)

Example:

>>> from transformers import FlaubertTokenizer, TFFlaubertModel
>>> import tensorflow as tf

>>> tokenizer = FlaubertTokenizer.from_pretrained('flaubert/flaubert_base_cased')
>>> model = TFFlaubertModel.from_pretrained('flaubert/flaubert_base_cased')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> outputs = model(inputs)

>>> last_hidden_states = outputs.last_hidden_state

TFFlaubertWithLMHeadModel¶

class transformers.TFFlaubertWithLMHeadModel(*args, **kwargs)[source]¶

The Flaubert Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).

This model inherits from TFPreTrainedModel. 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 tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

a single Tensor with input_ids only and nothing else: model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Parameters: config (FlaubertConfig) – 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.

call(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, training=False, **kwargs)[source]¶

The TFFlaubertWithLMHeadModel forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using FlaubertTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

What are input IDs?
attention_mask (Numpy array or tf.Tensor 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?
langs (tf.Tensor or Numpy array of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
token_type_ids (tf.Tensor or Numpy array 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 (tf.Tensor or Numpy array 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.max_position_embeddings - 1].

What are position IDs?
lengths (tf.Tensor or Numpy array of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility Indices selected in [0, ..., input_ids.size(-1)]:
cache (Dict[str, tf.Tensor], optional) –
Dictionary string to tf.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
inputs_embeds (tf.Tensor 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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

Returns

A TFFlaubertWithLMHeadModelOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (FlaubertConfig) and inputs.

logits (tf.Tensor 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(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + 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 initial embedding outputs.
attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Return type

TFFlaubertWithLMHeadModelOutput or tuple(tf.Tensor)

Example:

>>> from transformers import FlaubertTokenizer, TFFlaubertWithLMHeadModel
>>> import tensorflow as tf

>>> tokenizer = FlaubertTokenizer.from_pretrained('flaubert/flaubert_base_cased')
>>> model = TFFlaubertWithLMHeadModel.from_pretrained('flaubert/flaubert_base_cased')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> outputs = model(inputs)
>>> logits = outputs.logits

TFFlaubertForSequenceClassification¶

class transformers.TFFlaubertForSequenceClassification(*args, **kwargs)[source]¶

Flaubert Model 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 TFPreTrainedModel. 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 tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

a single Tensor with input_ids only and nothing else: model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Parameters: config (FlaubertConfig) – 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.

call(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, labels=None, training=False, **kwargs)¶

The TFXLMForSequenceClassification forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using BertTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

What are input IDs?
attention_mask (Numpy array or tf.Tensor 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?
langs (tf.Tensor or Numpy array of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
token_type_ids (Numpy array or tf.Tensor 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 (Numpy array or tf.Tensor 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.max_position_embeddings - 1].

What are position IDs?
lengths (tf.Tensor or Numpy array of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, tf.Tensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
inputs_embeds (tf.Tensor 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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
labels (tf.Tensor 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).

Returns

A TFSequenceClassifierOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (XLMConfig) and inputs.

loss (tf.Tensor of shape (batch_size, ), optional, returned when labels is provided) – Classification (or regression if config.num_labels==1) loss.
logits (tf.Tensor of shape (batch_size, config.num_labels)) – Classification (or regression if config.num_labels==1) scores (before SoftMax).
hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + 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 initial embedding outputs.
attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Return type

TFSequenceClassifierOutput or tuple(tf.Tensor)

Example:

>>> from transformers import XLMTokenizer, TFXLMForSequenceClassification
>>> import tensorflow as tf

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = TFXLMForSequenceClassification.from_pretrained('xlm-mlm-en-2048')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> inputs["labels"] = tf.reshape(tf.constant(1), (-1, 1)) # Batch size 1

>>> outputs = model(inputs)
>>> loss = outputs.loss
>>> logits = outputs.logits

TFFlaubertForMultipleChoice¶

class transformers.TFFlaubertForMultipleChoice(*args, **kwargs)[source]¶

Flaubert 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 TFPreTrainedModel. 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 tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

a single Tensor with input_ids only and nothing else: model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Parameters: config (FlaubertConfig) – 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.

call(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, labels=None, training=False, **kwargs)¶

The TFXLMForMultipleChoice forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (Numpy array or tf.Tensor of shape (batch_size, num_choices, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using BertTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

What are input IDs?
attention_mask (Numpy array or tf.Tensor of shape (batch_size, num_choices, 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?
langs (tf.Tensor or Numpy array of shape (batch_size, num_choices, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
token_type_ids (Numpy array or tf.Tensor 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 (Numpy array or tf.Tensor 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?
lengths (tf.Tensor or Numpy array of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, tf.Tensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
inputs_embeds (tf.Tensor 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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

Returns

A TFMultipleChoiceModelOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (XLMConfig) and inputs.

loss (tf.Tensor of shape (batch_size, ), optional, returned when labels is provided) – Classification loss.
logits (tf.Tensor 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(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + 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 initial embedding outputs.
attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Return type

TFMultipleChoiceModelOutput or tuple(tf.Tensor)

Example:

>>> from transformers import XLMTokenizer, TFXLMForMultipleChoice
>>> import tensorflow as tf

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = TFXLMForMultipleChoice.from_pretrained('xlm-mlm-en-2048')

>>> 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."

>>> encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors='tf', padding=True)
>>> inputs = {k: tf.expand_dims(v, 0) for k, v in encoding.items()}
>>> outputs = model(inputs)  # batch size is 1

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

TFFlaubertForTokenClassification¶

class transformers.TFFlaubertForTokenClassification(*args, **kwargs)[source]¶

Flaubert Model 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 TFPreTrainedModel. 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 tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

a single Tensor with input_ids only and nothing else: model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Parameters: config (FlaubertConfig) – 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.

call(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, labels=None, training=False, **kwargs)¶

The TFXLMForTokenClassification forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using BertTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

What are input IDs?
attention_mask (Numpy array or tf.Tensor 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?
langs (tf.Tensor or Numpy array of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
token_type_ids (Numpy array or tf.Tensor 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 (Numpy array or tf.Tensor 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.max_position_embeddings - 1].

What are position IDs?
lengths (tf.Tensor or Numpy array of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, tf.Tensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
inputs_embeds (tf.Tensor 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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
labels (tf.Tensor of shape (batch_size, sequence_length), optional) – Labels for computing the token classification loss. Indices should be in [0, ..., config.num_labels - 1].

Returns

A TFTokenClassifierOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (XLMConfig) and inputs.

loss (tf.Tensor of shape (n,), optional, where n is the number of unmasked labels, returned when labels is provided) – Classification loss.
logits (tf.Tensor of shape (batch_size, sequence_length, config.num_labels)) – Classification scores (before SoftMax).
hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + 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 initial embedding outputs.
attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Return type

TFTokenClassifierOutput or tuple(tf.Tensor)

Example:

>>> from transformers import XLMTokenizer, TFXLMForTokenClassification
>>> import tensorflow as tf

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = TFXLMForTokenClassification.from_pretrained('xlm-mlm-en-2048')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> input_ids = inputs["input_ids"]
>>> inputs["labels"] = tf.reshape(tf.constant([1] * tf.size(input_ids).numpy()), (-1, tf.size(input_ids))) # Batch size 1

>>> outputs = model(inputs)
>>> loss = outputs.loss
>>> logits = outputs.logits

TFFlaubertForQuestionAnsweringSimple¶

class transformers.TFFlaubertForQuestionAnsweringSimple(*args, **kwargs)[source]¶

Flaubert Model 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 TFPreTrainedModel. 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 tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

Note

TF 2.0 models accepts two formats as inputs:

having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.

This second option is useful when using tf.keras.Model.fit() method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

a single Tensor with input_ids only and nothing else: model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: model([input_ids, attention_mask]) or model([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring: model({"input_ids": input_ids, "token_type_ids": token_type_ids})

Parameters: config (FlaubertConfig) – 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.

call(input_ids=None, attention_mask=None, langs=None, token_type_ids=None, position_ids=None, lengths=None, cache=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, start_positions=None, end_positions=None, training=False, **kwargs)¶

The TFXLMForQuestionAnsweringSimple forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (Numpy array or tf.Tensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary.

Indices can be obtained using BertTokenizer. See transformers.PreTrainedTokenizer.__call__() and transformers.PreTrainedTokenizer.encode() for details.

What are input IDs?
attention_mask (Numpy array or tf.Tensor 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?
langs (tf.Tensor or Numpy array of shape (batch_size, sequence_length), optional) –
A parallel sequence of tokens to be used to indicate the language of each token in the input. Indices are languages ids which can be obtained from the language names by using two conversion mappings provided in the configuration of the model (only provided for multilingual models). More precisely, the language name to language id mapping is in model.config.lang2id (which is a dictionary string to int) and the language id to language name mapping is in model.config.id2lang (dictionary int to string).

See usage examples detailed in the multilingual documentation.
token_type_ids (Numpy array or tf.Tensor 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 (Numpy array or tf.Tensor 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.max_position_embeddings - 1].

What are position IDs?
lengths (tf.Tensor or Numpy array of shape (batch_size,), optional) – Length of each sentence that can be used to avoid performing attention on padding token indices. You can also use attention_mask for the same result (see above), kept here for compatibility. Indices selected in [0, ..., input_ids.size(-1)].
cache (Dict[str, tf.Tensor], optional) –
Dictionary string to torch.FloatTensor that contains precomputed hidden states (key and values in the attention blocks) as computed by the model (see cache output below). Can be used to speed up sequential decoding.

The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
head_mask (Numpy array or tf.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) –
Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
inputs_embeds (tf.Tensor 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.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
training (bool, optional, defaults to False) – Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
start_positions (tf.Tensor 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 (tf.Tensor 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.

Returns

A TFQuestionAnsweringModelOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (XLMConfig) and inputs.

loss (tf.Tensor of shape (batch_size, ), optional, returned when start_positions and end_positions are provided) – Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.
start_logits (tf.Tensor of shape (batch_size, sequence_length)) – Span-start scores (before SoftMax).
end_logits (tf.Tensor of shape (batch_size, sequence_length)) – Span-end scores (before SoftMax).
hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of tf.Tensor (one for the output of the embeddings + 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 initial embedding outputs.
attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of tf.Tensor (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.

Return type

TFQuestionAnsweringModelOutput or tuple(tf.Tensor)

Example:

>>> from transformers import XLMTokenizer, TFXLMForQuestionAnsweringSimple
>>> import tensorflow as tf

>>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
>>> model = TFXLMForQuestionAnsweringSimple.from_pretrained('xlm-mlm-en-2048')

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
>>> input_dict = tokenizer(question, text, return_tensors='tf')
>>> outputs = model(input_dict)
>>> start_logits = outputs.start_logits
>>> end_logits = outputs.end_logits

>>> all_tokens = tokenizer.convert_ids_to_tokens(input_dict["input_ids"].numpy()[0])
>>> answer = ' '.join(all_tokens[tf.math.argmax(start_logits, 1)[0] : tf.math.argmax(end_logits, 1)[0]+1])