# BART¶

DISCLAIMER: If you see something strange, file a Github Issue and assign @patrickvonplaten

## Overview¶

The Bart model was proposed in BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer on 29 Oct, 2019.

According to the abstract,

• Bart uses a standard seq2seq/machine translation architecture with a bidirectional encoder (like BERT) and a left-to-right decoder (like GPT).

• The pretraining task involves randomly shuffling the order of the original sentences and a novel in-filling scheme, where spans of text are replaced with a single mask token.

• BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa with comparable training resources on GLUE and SQuAD, achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 6 ROUGE.

This model was contributed by sshleifer. The Authors’ code can be found here.

## Implementation Notes¶

• Bart doesn’t use token_type_ids for sequence classification. Use BartTokenizer or encode() to get the proper splitting.

• The forward pass of BartModel will create the decoder_input_ids if they are not passed. This is different than some other modeling APIs. A typical use case of this feature is mask filling.

• Model predictions are intended to be identical to the original implementation when force_bos_token_to_be_generated=True. This only works, however, if the string you pass to fairseq.encode() starts with a space.

• generate() should be used for conditional generation tasks like summarization, see the example in that docstrings.

• Models that load the facebook/bart-large-cnn weights will not have a mask_token_id, or be able to perform mask-filling tasks.

The facebook/bart-base and facebook/bart-large checkpoints can be used to fill multi-token masks.

from transformers import BartForConditionalGeneration, BartTokenizer
example_english_phrase = "UN Chief Says There Is No <mask> in Syria"
batch = tok(example_english_phrase, return_tensors='pt')
generated_ids = model.generate(batch['input_ids'])
assert tok.batch_decode(generated_ids, skip_special_tokens=True) == ['UN Chief Says There Is No Plan to Stop Chemical Weapons in Syria']


## BartConfig¶

class transformers.BartConfig(vocab_size=50265, max_position_embeddings=1024, encoder_layers=12, encoder_ffn_dim=4096, encoder_attention_heads=16, decoder_layers=12, decoder_ffn_dim=4096, decoder_attention_heads=16, encoder_layerdrop=0.0, decoder_layerdrop=0.0, activation_function='gelu', d_model=1024, dropout=0.1, attention_dropout=0.0, activation_dropout=0.0, init_std=0.02, classifier_dropout=0.0, scale_embedding=False, use_cache=True, num_labels=3, pad_token_id=1, bos_token_id=0, eos_token_id=2, is_encoder_decoder=True, decoder_start_token_id=2, forced_eos_token_id=2, **kwargs)[source]

This is the configuration class to store the configuration of a BartModel. It is used to instantiate a BART model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the BART facebook/bart-large architecture.

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

Parameters
• vocab_size (int, optional, defaults to 50265) – Vocabulary size of the BART model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling BartModel or TFBartModel.

• d_model (int, optional, defaults to 1024) – Dimensionality of the layers and the pooler layer.

• encoder_layers (int, optional, defaults to 12) – Number of encoder layers.

• decoder_layers (int, optional, defaults to 12) – Number of decoder layers.

• encoder_attention_heads (int, optional, defaults to 16) – Number of attention heads for each attention layer in the Transformer encoder.

• decoder_attention_heads (int, optional, defaults to 16) – Number of attention heads for each attention layer in the Transformer decoder.

• decoder_ffn_dim (int, optional, defaults to 4096) – Dimensionality of the “intermediate” (often named feed-forward) layer in decoder.

• encoder_ffn_dim (int, optional, defaults to 4096) – Dimensionality of the “intermediate” (often named feed-forward) layer in decoder.

• activation_function (str or function, optional, defaults to "gelu") – The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "silu" and "gelu_new" are supported.

• 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 0.0) – The dropout ratio for the attention probabilities.

• activation_dropout (float, optional, defaults to 0.0) – The dropout ratio for activations inside the fully connected layer.

• classifier_dropout (float, optional, defaults to 0.0) – The dropout ratio for classifier.

• max_position_embeddings (int, optional, defaults to 1024) – 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).

• init_std (float, optional, defaults to 0.02) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

• encoder_layerdrop – (float, optional, defaults to 0.0): The LayerDrop probability for the encoder. See the LayerDrop paper for more details.

• decoder_layerdrop – (float, optional, defaults to 0.0): The LayerDrop probability for the decoder. See the LayerDrop paper for more details.

• scale_embedding (bool, optional, defaults to False) – Scale embeddings by diving by sqrt(d_model).

• use_cache (bool, optional, defaults to True) – Whether or not the model should return the last key/values attentions (not used by all models).

• num_labels – (int, optional, defaults to 3): The number of labels to use in BartForSequenceClassification.

• forced_eos_token_id (int, optional, defaults to 2) – The id of the token to force as the last generated token when max_length is reached. Usually set to eos_token_id.

Example:

>>> from transformers import BartModel, BartConfig

>>> # Initializing a BART facebook/bart-large style configuration
>>> configuration = BartConfig()

>>> # Initializing a model from the facebook/bart-large style configuration
>>> model = BartModel(configuration)

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


## BartTokenizer¶

class transformers.BartTokenizer(vocab_file, merges_file, errors='replace', bos_token='<s>', eos_token='</s>', sep_token='</s>', cls_token='<s>', unk_token='<unk>', pad_token='<pad>', mask_token='<mask>', add_prefix_space=False, **kwargs)[source]

Construct a BART tokenizer.

BartTokenizer is identical to RobertaTokenizer. Refer to superclass RobertaTokenizer for usage examples and documentation concerning the initialization parameters and other methods.

## BartTokenizerFast¶

class transformers.BartTokenizerFast(vocab_file=None, merges_file=None, tokenizer_file=None, errors='replace', bos_token='<s>', eos_token='</s>', sep_token='</s>', cls_token='<s>', unk_token='<unk>', pad_token='<pad>', mask_token='<mask>', add_prefix_space=False, **kwargs)[source]

Construct a “fast” BART tokenizer (backed by HuggingFace’s tokenizers library).

BartTokenizerFast is identical to RobertaTokenizerFast. Refer to superclass RobertaTokenizerFast for usage examples and documentation concerning the initialization parameters and other methods.

slow_tokenizer_class

alias of transformers.models.bart.tokenization_bart.BartTokenizer

## BartModel¶

class transformers.BartModel(config: transformers.models.bart.configuration_bart.BartConfig)[source]

The bare BART Model outputting raw hidden-states without any specific head on top. This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

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

Parameters

config (BartConfig) – 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, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, cross_attn_head_mask=None, encoder_outputs=None, past_key_values=None, inputs_embeds=None, decoder_inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]

The BartModel 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. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (torch.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.

• decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

Bart uses the eos_token_id as the starting token for decoder_input_ids generation. If past_key_values is used, optionally only the last decoder_input_ids have to be input (see past_key_values).

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (torch.LongTensor of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should read modeling_bart._prepare_decoder_inputs() and modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• head_mask (torch.Tensor of shape (encoder_layers, encoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

• decoder_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

• cross_attn_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in [0, 1]:

• encoder_outputs (tuple(tuple(torch.FloatTensor), optional) – Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) –

Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

• 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.

• decoder_inputs_embeds (torch.FloatTensor of shape (batch_size, target_sequence_length, hidden_size), optional) –

Optionally, instead of passing decoder_input_ids you can choose to directly pass an embedded representation. If past_key_values is used, optionally only the last decoder_inputs_embeds have to be input (see past_key_values). This is useful if you want more control over how to convert decoder_input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

If decoder_input_ids and decoder_inputs_embeds are both unset, decoder_inputs_embeds takes the value of inputs_embeds.

• use_cache (bool, optional) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

• 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 Seq2SeqModelOutput 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 (BartConfig) 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 decoder of the model.

If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

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

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

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

• encoder_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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

Seq2SeqModelOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import BartTokenizer, BartModel
>>> import torch

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

>>> last_hidden_states = outputs.last_hidden_state


## BartForConditionalGeneration¶

class transformers.BartForConditionalGeneration(config: transformers.models.bart.configuration_bart.BartConfig)[source]

The BART Model with a language modeling head. Can be used for summarization. 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 (BartConfig) – 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, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, cross_attn_head_mask=None, encoder_outputs=None, past_key_values=None, inputs_embeds=None, decoder_inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]

The BartForConditionalGeneration 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. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (torch.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.

• decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

Bart uses the eos_token_id as the starting token for decoder_input_ids generation. If past_key_values is used, optionally only the last decoder_input_ids have to be input (see past_key_values).

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (torch.LongTensor of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should read modeling_bart._prepare_decoder_inputs() and modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• head_mask (torch.Tensor of shape (encoder_layers, encoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

• decoder_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

• cross_attn_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in [0, 1]:

• encoder_outputs (tuple(tuple(torch.FloatTensor), optional) – Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) –

Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

• 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.

• decoder_inputs_embeds (torch.FloatTensor of shape (batch_size, target_sequence_length, hidden_size), optional) –

Optionally, instead of passing decoder_input_ids you can choose to directly pass an embedded representation. If past_key_values is used, optionally only the last decoder_inputs_embeds have to be input (see past_key_values). This is useful if you want more control over how to convert decoder_input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

If decoder_input_ids and decoder_inputs_embeds are both unset, decoder_inputs_embeds takes the value of inputs_embeds.

• use_cache (bool, optional) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

• 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 masked language modeling loss. Indices should either be in [0, ..., config.vocab_size] or -100 (see input_ids docstring). Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size].

Returns

A Seq2SeqLMOutput 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 (BartConfig) and inputs.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) – Language modeling 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).

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

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

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

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

• encoder_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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

Seq2SeqLMOutput or tuple(torch.FloatTensor)

Summarization example:

>>> from transformers import BartTokenizer, BartForConditionalGeneration, BartConfig

>>> ARTICLE_TO_SUMMARIZE = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer([ARTICLE_TO_SUMMARIZE], max_length=1024, return_tensors='pt')

>>> # Generate Summary
>>> summary_ids = model.generate(inputs['input_ids'], num_beams=4, max_length=5, early_stopping=True)
>>> print([tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=False) for g in summary_ids])


>>> from transformers import BartTokenizer, BartForConditionalGeneration
>>> TXT = "My friends are <mask> but they eat too many carbs."

>>> input_ids = tokenizer([TXT], return_tensors='pt')['input_ids']
>>> logits = model(input_ids).logits

>>> values, predictions = probs.topk(5)

>>> tokenizer.decode(predictions).split()


## BartForSequenceClassification¶

class transformers.BartForSequenceClassification(config: transformers.models.bart.configuration_bart.BartConfig, **kwargs)[source]

Bart model with a sequence classification/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 (BartConfig) – 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, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, cross_attn_head_mask=None, encoder_outputs=None, inputs_embeds=None, decoder_inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]

The BartForSequenceClassification 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. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (torch.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.

• decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

Bart uses the eos_token_id as the starting token for decoder_input_ids generation. If past_key_values is used, optionally only the last decoder_input_ids have to be input (see past_key_values).

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (torch.LongTensor of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should read modeling_bart._prepare_decoder_inputs() and modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• head_mask (torch.Tensor of shape (encoder_layers, encoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

• decoder_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

• cross_attn_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in [0, 1]:

• encoder_outputs (tuple(tuple(torch.FloatTensor), optional) – Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) –

Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

• 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.

• decoder_inputs_embeds (torch.FloatTensor of shape (batch_size, target_sequence_length, hidden_size), optional) –

Optionally, instead of passing decoder_input_ids you can choose to directly pass an embedded representation. If past_key_values is used, optionally only the last decoder_inputs_embeds have to be input (see past_key_values). This is useful if you want more control over how to convert decoder_input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

If decoder_input_ids and decoder_inputs_embeds are both unset, decoder_inputs_embeds takes the value of inputs_embeds.

• use_cache (bool, optional) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

• 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 classification loss is computed (Cross-Entropy).

Returns

A Seq2SeqSequenceClassifierOutput 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 (BartConfig) and inputs.

• loss (torch.FloatTensor of shape (1,), optional, returned when label 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).

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

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

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

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

• encoder_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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

Seq2SeqSequenceClassifierOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import BartTokenizer, BartForSequenceClassification
>>> import torch

>>> 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


class transformers.BartForQuestionAnswering(config)[source]

BART 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 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 (BartConfig) – 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, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, cross_attn_head_mask=None, encoder_outputs=None, start_positions=None, end_positions=None, inputs_embeds=None, decoder_inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]

The BartForQuestionAnswering 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. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (torch.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.

• decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

Bart uses the eos_token_id as the starting token for decoder_input_ids generation. If past_key_values is used, optionally only the last decoder_input_ids have to be input (see past_key_values).

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (torch.LongTensor of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should read modeling_bart._prepare_decoder_inputs() and modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• head_mask (torch.Tensor of shape (encoder_layers, encoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

• decoder_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

• cross_attn_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in [0, 1]:

• encoder_outputs (tuple(tuple(torch.FloatTensor), optional) – Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) –

Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

• 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.

• decoder_inputs_embeds (torch.FloatTensor of shape (batch_size, target_sequence_length, hidden_size), optional) –

Optionally, instead of passing decoder_input_ids you can choose to directly pass an embedded representation. If past_key_values is used, optionally only the last decoder_inputs_embeds have to be input (see past_key_values). This is useful if you want more control over how to convert decoder_input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

If decoder_input_ids and decoder_inputs_embeds are both unset, decoder_inputs_embeds takes the value of inputs_embeds.

• use_cache (bool, optional) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

• 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 Seq2SeqQuestionAnsweringModelOutput 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 (BartConfig) 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).

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

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

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

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

• encoder_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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

Seq2SeqQuestionAnsweringModelOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import BartTokenizer, BartForQuestionAnswering
>>> import torch

>>> 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


## BartForCausalLM¶

class transformers.BartForCausalLM(config)[source]
forward(input_ids=None, attention_mask=None, encoder_hidden_states=None, encoder_attention_mask=None, head_mask=None, cross_attn_head_mask=None, past_key_values=None, inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]
Args:
input_ids (torch.LongTensor of shape (batch_size, sequence_length)):

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

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

What are input IDs?

attention_mask (torch.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.

encoder_hidden_states (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional):

Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.

encoder_attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional):

Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:

head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional):

Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]:

cross_attn_head_mask (torch.Tensor of shape (decoder_layers, decoder_attention_heads), optional):

Mask to nullify selected heads of the cross-attention modules. Mask values selected in [0, 1]:

past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True):

Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head). The two additional tensors are only required when the model is used as a decoder in a Sequence to Sequence model.

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

labels (torch.LongTensor of shape (batch_size, sequence_length), optional):

Labels for computing the masked language modeling loss. Indices should either be in [0, ..., config.vocab_size] or -100 (see input_ids docstring). Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size].

use_cache (bool, optional):

If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

• 1 for tokens that are not masked,

• 0 for tokens that are masked.

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 CausalLMOutputWithCrossAttentions 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 (BartConfig) and inputs.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) – Language modeling loss (for next-token prediction).

• 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.

• cross_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).

Cross attentions weights after the attention softmax, used to compute the weighted average in the cross-attention heads.

• past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of torch.FloatTensor tuples of length config.n_layers, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant if config.is_decoder = True.

Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

Example:

>>> from transformers import BartTokenizer, BartForCausalLM

>>> assert model.config.is_decoder, f"{model.__class__} has to be configured as a decoder."
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state


Return type

CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)

## TFBartModel¶

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

The bare BART Model 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(input_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 (BartConfig) – 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, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, cross_attn_head_mask=None, encoder_outputs: Optional[Union[Tuple, transformers.modeling_tf_outputs.TFBaseModelOutput]] = None, past_key_values=None, inputs_embeds=None, decoder_inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, training=False, **kwargs)[source]

The TFBartModel 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 (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.encode() and transformers.PreTrainedTokenizer.__call__() for details.

What are input IDs?

• attention_mask (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.

• decoder_input_ids (tf.Tensor of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

Bart uses the eos_token_id as the starting token for decoder_input_ids generation. If past_key_values is used, optionally only the last decoder_input_ids have to be input (see past_key_values).

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (tf.Tensor of shape (batch_size, target_sequence_length), optional) – will be made by default and ignore pad tokens. It is not recommended to set this for most use cases.

• head_mask (tf.Tensor of shape (encoder_layers, encoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

• decoder_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

• cross_attn_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the cross-attention modules. Mask values selected in [0, 1]:

• encoder_outputs (tf.FloatTensor, optional) – hidden states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. of shape (batch_size, sequence_length, hidden_size) is a sequence of

• past_key_values (Tuple[Tuple[tf.Tensor]] of length config.n_layers) – contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

• use_cache (bool, optional, defaults to True) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values). Set to False during training, True during generation

• 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 TFSeq2SeqModelOutput 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 (BartConfig) 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 decoder of the model.

If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.

• past_key_values (List[tf.Tensor], optional, returned when use_cache=True is passed or when config.use_cache=True) – List of tf.Tensor of length config.n_layers, with each tensor of shape (2, batch_size, num_heads, sequence_length, embed_size_per_head)).

Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

• cross_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 of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

• encoder_last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) – Sequence of hidden-states at the output of the last layer of the encoder of the model.

• encoder_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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

TFSeq2SeqModelOutput or tuple(tf.Tensor)

Example:

>>> from transformers import BartTokenizer, TFBartModel
>>> import tensorflow as tf

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

>>> last_hidden_states = outputs.last_hidden_state


## TFBartForConditionalGeneration¶

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

The BART Model with a language modeling head. Can be used for summarization. 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(input_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 (BartConfig) – 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, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, cross_attn_head_mask=None, encoder_outputs: = None, past_key_values=None, inputs_embeds=None, decoder_inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, labels=None, training=False, **kwargs)[source]

The TFBartForConditionalGeneration 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 (tf.Tensor of shape ({0})) –

Indices of input sequence tokens in the vocabulary.

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

What are input IDs?

• attention_mask (tf.Tensor of shape ({0}), 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.

• decoder_input_ids (tf.Tensor of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

Bart uses the eos_token_id as the starting token for decoder_input_ids generation. If past_key_values is used, optionally only the last decoder_input_ids have to be input (see past_key_values).

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (tf.Tensor of shape (batch_size, target_sequence_length), optional) – will be made by default and ignore pad tokens. It is not recommended to set this for most use cases.

• head_mask (tf.Tensor of shape (encoder_layers, encoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in [0, 1]:

• decoder_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in [0, 1]:

• cross_attn_head_mask (tf.Tensor of shape (decoder_layers, decoder_attention_heads), optional) –

Mask to nullify selected heads of the cross-attention modules. Mask values selected in [0, 1]:

• encoder_outputs (tf.FloatTensor, optional) – hidden states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. of shape (batch_size, sequence_length, hidden_size) is a sequence of

• past_key_values (Tuple[Tuple[tf.Tensor]] of length config.n_layers) – contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

• use_cache (bool, optional, defaults to True) – If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values). Set to False during training, True during generation

• 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 masked language modeling loss. Indices should either be in [0, ..., config.vocab_size] or -100 (see input_ids docstring). Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size].

Returns

A TFSeq2SeqLMOutput 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 (BartConfig) and inputs.

• loss (tf.Tensor of shape (n,), optional, where n is the number of non-masked labels, returned when labels is provided) – Language modeling loss.

• 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).

• past_key_values (List[tf.Tensor], optional, returned when use_cache=True is passed or when config.use_cache=True) – List of tf.Tensor of length config.n_layers, with each tensor of shape (2, batch_size, num_heads, sequence_length, embed_size_per_head)).

Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

• cross_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 of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

• encoder_last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) – Sequence of hidden-states at the output of the last layer of the encoder of the model.

• encoder_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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

TFSeq2SeqLMOutput or tuple(tf.Tensor)

Summarization example:

>>> from transformers import BartTokenizer, TFBartForConditionalGeneration, BartConfig

>>> ARTICLE_TO_SUMMARIZE = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer([ARTICLE_TO_SUMMARIZE], max_length=1024, return_tensors='tf')

>>> # Generate Summary
>>> summary_ids = model.generate(inputs['input_ids'], num_beams=4, max_length=5, early_stopping=True)
>>> print([tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=False) for g in summary_ids])


>>> from transformers import BartTokenizer, TFBartForConditionalGeneration
>>> TXT = "My friends are <mask> but they eat too many carbs."

>>> input_ids = tokenizer([TXT], return_tensors='tf')['input_ids']
>>> logits = model(input_ids).logits
>>> probs = tf.nn.softmax(logits[0])
>>> # probs[5] is associated with the mask token


## FlaxBartModel¶

class transformers.FlaxBartModel(config: transformers.models.bart.configuration_bart.BartConfig, input_shape: Tuple[int] = (1, 1), seed: int = 0, dtype: numpy.dtype = <class 'jax._src.numpy.lax_numpy.float32'>, **kwargs)[source]

The bare Bart Model transformer outputting raw hidden-states without any specific head on top. This model inherits from FlaxPreTrainedModel. 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 Flax Linen flax.nn.Module subclass. Use it as a regular Flax Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

Parameters

config (BartConfig) – 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: jax._src.numpy.lax_numpy.ndarray, attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_input_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)

The FlaxBartPreTrainedModel 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 (jnp.ndarray of shape (batch_size, sequence_length)) –

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (jnp.ndarray 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.

• decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• position_ids (numpy.ndarray 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].

• decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) – Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

• 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 FlaxSeq2SeqModelOutput 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 (BartConfig) and inputs.

• last_hidden_state (jnp.ndarray of shape (batch_size, sequence_length, hidden_size)) – Sequence of hidden-states at the output of the last layer of the decoder of the model.

If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.

• past_key_values (tuple(tuple(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(jnp.ndarray) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

• cross_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

• encoder_last_hidden_state (jnp.ndarray of shape (batch_size, sequence_length, hidden_size), optional) – Sequence of hidden-states at the output of the last layer of the encoder of the model.

• encoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

Return type

FlaxSeq2SeqModelOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import BartTokenizer, FlaxBartModel

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

>>> last_hidden_states = outputs.last_hidden_state

decode(decoder_input_ids, encoder_outputs, encoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, past_key_values: dict = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)
Parameters
• decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length)) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• encoder_outputs (tuple(tuple(jnp.ndarray)) – Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• encoder_attention_mask (jnp.ndarray 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.

• decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) – Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

• past_key_values (Dict[str, np.ndarray], optional, returned by init_cache or when passing previous past_key_values) – Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape [batch_size, max_length].

• 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 FlaxBaseModelOutputWithPastAndCrossAttentions 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 (~transformers.) and inputs.

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

If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.

• past_key_values (tuple(tuple(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(jnp.ndarray) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and optionally if config.is_encoder_decoder=True 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if config.is_encoder_decoder=True in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

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

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

Example:

>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors='jax')
>>> encoder_outputs = model.encode(**inputs)

>>> decoder_start_token_id = model.config.decoder_start_token_id
>>> decoder_input_ids = jnp.ones((inputs.input_ids.shape[0], 1), dtype="i4") * decoder_start_token_id

>>> outputs = model.decode(decoder_input_ids, encoder_outputs)
>>> last_decoder_hidden_states = outputs.last_hidden_state


Return type

FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)

encode(input_ids: jax._src.numpy.lax_numpy.ndarray, attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)
Parameters
• input_ids (jnp.ndarray of shape (batch_size, sequence_length)) –

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (jnp.ndarray 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.

• position_ids (numpy.ndarray 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].

• 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 FlaxBaseModelOutput 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 (~transformers.) and inputs.

• last_hidden_state (jnp.ndarray 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(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (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 BartTokenizer, FlaxBartForConditionalGeneration

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors='jax')
>>> encoder_outputs = model.encode(**inputs)


Return type

FlaxBaseModelOutput or tuple(torch.FloatTensor)

## FlaxBartForConditionalGeneration¶

class transformers.FlaxBartForConditionalGeneration(config: transformers.models.bart.configuration_bart.BartConfig, input_shape: Tuple[int] = (1, 1), seed: int = 0, dtype: numpy.dtype = <class 'jax._src.numpy.lax_numpy.float32'>, **kwargs)[source]

The BART Model with a language modeling head. Can be used for summarization. This model inherits from FlaxPreTrainedModel. 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 Flax Linen flax.nn.Module subclass. Use it as a regular Flax Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

Parameters

config (BartConfig) – 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: jax._src.numpy.lax_numpy.ndarray, attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_input_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)

The FlaxBartPreTrainedModel 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 (jnp.ndarray of shape (batch_size, sequence_length)) –

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (jnp.ndarray 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.

• decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• position_ids (numpy.ndarray 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].

• decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) – Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

• 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 FlaxSeq2SeqLMOutput 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 (BartConfig) and inputs.

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

• past_key_values (tuple(tuple(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(jnp.ndarray) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

• cross_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

• encoder_last_hidden_state (jnp.ndarray of shape (batch_size, sequence_length, hidden_size), optional) – Sequence of hidden-states at the output of the last layer of the encoder of the model.

• encoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

Return type

FlaxSeq2SeqLMOutput or tuple(torch.FloatTensor)

Summarization example:

>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration

>>> ARTICLE_TO_SUMMARIZE = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer([ARTICLE_TO_SUMMARIZE], max_length=1024, return_tensors='jax')

>>> # Generate Summary
>>> summary_ids = model.generate(inputs['input_ids']).sequences
>>> print(tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False))


>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration
>>> TXT = "My friends are <mask> but they eat too many carbs."

>>> input_ids = tokenizer([TXT], return_tensors='jax')['input_ids']
>>> logits = model(input_ids).logits

>>> probs = jax.nn.softmax(logits[0, masked_index], axis=0)
>>> values, predictions = jax.lax.top_k(probs)

>>> tokenizer.decode(predictions).split()

decode(decoder_input_ids, encoder_outputs, encoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, past_key_values: dict = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)[source]
Parameters
• decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length)) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• encoder_outputs (tuple(tuple(jnp.ndarray)) – Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• encoder_attention_mask (jnp.ndarray 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.

• decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) – Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

• past_key_values (Dict[str, np.ndarray], optional, returned by init_cache or when passing previous past_key_values) – Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape [batch_size, max_length].

• 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 FlaxCausalLMOutputWithCrossAttentions 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 (~transformers.) and inputs.

• logits (jnp.ndarray 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(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

• cross_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Cross attentions weights after the attention softmax, used to compute the weighted average in the cross-attention heads.

• past_key_values (tuple(tuple(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of jnp.ndarray tuples of length config.n_layers, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant if config.is_decoder = True.

Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

Example:

>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors='jax')
>>> encoder_outputs = model.encode(**inputs)

>>> decoder_start_token_id = model.config.decoder_start_token_id
>>> decoder_input_ids = jnp.ones((inputs.input_ids.shape[0], 1), dtype="i4") * decoder_start_token_id

>>> outputs = model.decode(decoder_input_ids, encoder_outputs)
>>> logits = outputs.logits


Return type

FlaxCausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)

encode(input_ids: jax._src.numpy.lax_numpy.ndarray, attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)
Parameters
• input_ids (jnp.ndarray of shape (batch_size, sequence_length)) –

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (jnp.ndarray 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.

• position_ids (numpy.ndarray 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].

• 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 FlaxBaseModelOutput 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 (~transformers.) and inputs.

• last_hidden_state (jnp.ndarray 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(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (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 BartTokenizer, FlaxBartForConditionalGeneration

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors='jax')
>>> encoder_outputs = model.encode(**inputs)


Return type

FlaxBaseModelOutput or tuple(torch.FloatTensor)

## FlaxBartForSequenceClassification¶

class transformers.FlaxBartForSequenceClassification(config: transformers.models.bart.configuration_bart.BartConfig, input_shape: Tuple[int] = (1, 1), seed: int = 0, dtype: numpy.dtype = <class 'jax._src.numpy.lax_numpy.float32'>, **kwargs)[source]

Bart model with a sequence classification/head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.

This model inherits from FlaxPreTrainedModel. 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 Flax Linen flax.nn.Module subclass. Use it as a regular Flax Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

Parameters

config (BartConfig) – 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: jax._src.numpy.lax_numpy.ndarray, attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_input_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)

The FlaxBartPreTrainedModel 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 (jnp.ndarray of shape (batch_size, sequence_length)) –

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (jnp.ndarray 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.

• decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• position_ids (numpy.ndarray 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].

• decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) – Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

• 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 FlaxSeq2SeqSequenceClassifierOutput 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 (BartConfig) and inputs.

• logits (jnp.ndarray of shape (batch_size, config.num_labels)) – Classification (or regression if config.num_labels==1) scores (before SoftMax).

• past_key_values (tuple(tuple(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(jnp.ndarray) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

• cross_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

• encoder_last_hidden_state (jnp.ndarray of shape (batch_size, sequence_length, hidden_size), optional) – Sequence of hidden-states at the output of the last layer of the encoder of the model.

• encoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

Return type

FlaxSeq2SeqSequenceClassifierOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import BartTokenizer, FlaxBartForSequenceClassification

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

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

decode(decoder_input_ids, encoder_outputs, encoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, past_key_values: dict = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)
Parameters
• decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length)) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• encoder_outputs (tuple(tuple(jnp.ndarray)) – Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• encoder_attention_mask (jnp.ndarray 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.

• decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) – Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

• past_key_values (Dict[str, np.ndarray], optional, returned by init_cache or when passing previous past_key_values) – Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape [batch_size, max_length].

• 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 FlaxBaseModelOutputWithPastAndCrossAttentions 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 (~transformers.) and inputs.

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

If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.

• past_key_values (tuple(tuple(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(jnp.ndarray) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and optionally if config.is_encoder_decoder=True 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if config.is_encoder_decoder=True in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

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

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

Example:

>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors='jax')
>>> encoder_outputs = model.encode(**inputs)

>>> decoder_start_token_id = model.config.decoder_start_token_id
>>> decoder_input_ids = jnp.ones((inputs.input_ids.shape[0], 1), dtype="i4") * decoder_start_token_id

>>> outputs = model.decode(decoder_input_ids, encoder_outputs)
>>> last_decoder_hidden_states = outputs.last_hidden_state


Return type

FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)

encode(input_ids: jax._src.numpy.lax_numpy.ndarray, attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)
Parameters
• input_ids (jnp.ndarray of shape (batch_size, sequence_length)) –

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (jnp.ndarray 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.

• position_ids (numpy.ndarray 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].

• 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 FlaxBaseModelOutput 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 (~transformers.) and inputs.

• last_hidden_state (jnp.ndarray 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(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (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 BartTokenizer, FlaxBartForConditionalGeneration

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors='jax')
>>> encoder_outputs = model.encode(**inputs)


Return type

FlaxBaseModelOutput or tuple(torch.FloatTensor)

class transformers.FlaxBartForQuestionAnswering(config: transformers.models.bart.configuration_bart.BartConfig, input_shape: Tuple[int] = (1, 1), seed: int = 0, dtype: numpy.dtype = <class 'jax._src.numpy.lax_numpy.float32'>, **kwargs)[source]

BART 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 FlaxPreTrainedModel. 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 Flax Linen flax.nn.Module subclass. Use it as a regular Flax Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

Parameters

config (BartConfig) – 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: jax._src.numpy.lax_numpy.ndarray, attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_input_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)

The FlaxBartPreTrainedModel 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 (jnp.ndarray of shape (batch_size, sequence_length)) –

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (jnp.ndarray 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.

• decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• position_ids (numpy.ndarray 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].

• decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) – Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

• 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 FlaxSeq2SeqQuestionAnsweringModelOutput 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 (BartConfig) and inputs.

• start_logits (jnp.ndarray of shape (batch_size, sequence_length)) – Span-start scores (before SoftMax).

• end_logits (jnp.ndarray of shape (batch_size, sequence_length)) – Span-end scores (before SoftMax).

• past_key_values (tuple(tuple(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(jnp.ndarray) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• decoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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 decoder at the output of each layer plus the initial embedding outputs.

• decoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

• cross_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

• encoder_last_hidden_state (jnp.ndarray of shape (batch_size, sequence_length, hidden_size), optional) – Sequence of hidden-states at the output of the last layer of the encoder of the model.

• encoder_hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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 encoder at the output of each layer plus the initial embedding outputs.

• encoder_attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

Return type

FlaxSeq2SeqQuestionAnsweringModelOutput or tuple(torch.FloatTensor)

Example:

>>> from transformers import BartTokenizer, FlaxBartForQuestionAnswering

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
>>> inputs = tokenizer(question, text, return_tensors='jax')

>>> outputs = model(**inputs)
>>> start_scores = outputs.start_logits
>>> end_scores = outputs.end_logits

decode(decoder_input_ids, encoder_outputs, encoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, decoder_position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, past_key_values: dict = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)
Parameters
• decoder_input_ids (jnp.ndarray of shape (batch_size, target_sequence_length)) –

Indices of decoder input sequence tokens in the vocabulary.

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

What are decoder input IDs?

For translation and summarization training, decoder_input_ids should be provided. If no decoder_input_ids is provided, the model will create this tensor by shifting the input_ids to the right for denoising pre-training following the paper.

• encoder_outputs (tuple(tuple(jnp.ndarray)) – Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• encoder_attention_mask (jnp.ndarray 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.

• decoder_attention_mask (jnp.ndarray of shape (batch_size, target_sequence_length), optional) –

Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.

If you want to change padding behavior, you should modify to your needs. See diagram 1 in the paper for more information on the default strategy.

• decoder_position_ids (numpy.ndarray of shape (batch_size, sequence_length), optional) – Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

• past_key_values (Dict[str, np.ndarray], optional, returned by init_cache or when passing previous past_key_values) – Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape [batch_size, max_length].

• 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 FlaxBaseModelOutputWithPastAndCrossAttentions 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 (~transformers.) and inputs.

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

If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.

• past_key_values (tuple(tuple(jnp.ndarray)), optional, returned when use_cache=True is passed or when config.use_cache=True) – Tuple of tuple(jnp.ndarray) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and optionally if config.is_encoder_decoder=True 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if config.is_encoder_decoder=True in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

• hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

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

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

Example:

>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors='jax')
>>> encoder_outputs = model.encode(**inputs)

>>> decoder_start_token_id = model.config.decoder_start_token_id
>>> decoder_input_ids = jnp.ones((inputs.input_ids.shape[0], 1), dtype="i4") * decoder_start_token_id

>>> outputs = model.decode(decoder_input_ids, encoder_outputs)
>>> last_decoder_hidden_states = outputs.last_hidden_state


Return type

FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)

encode(input_ids: jax._src.numpy.lax_numpy.ndarray, attention_mask: Optional[jax._src.numpy.lax_numpy.ndarray] = None, position_ids: Optional[jax._src.numpy.lax_numpy.ndarray] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, train: bool = False, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None)
Parameters
• input_ids (jnp.ndarray of shape (batch_size, sequence_length)) –

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

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

What are input IDs?

• attention_mask (jnp.ndarray 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.

• position_ids (numpy.ndarray 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].

• 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 FlaxBaseModelOutput 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 (~transformers.) and inputs.

• last_hidden_state (jnp.ndarray 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(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (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(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (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 BartTokenizer, FlaxBartForConditionalGeneration


FlaxBaseModelOutput or tuple(torch.FloatTensor)