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 Authorsβ code can be found here.
Examples
- Examples and scripts for fine-tuning BART and other models for sequence to sequence tasks can be found in examples/pytorch/summarization/.
- An example of how to train BartForConditionalGeneration with a Hugging Face
datasets
object can be found in this forum discussion. - Distilled checkpoints are described in this paper.
Implementation Notes
- Bart doesnβt 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 tofairseq.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.
Mask Filling
The facebook/bart-base
and facebook/bart-large
checkpoints can be used to fill multi-token masks.
from transformers import BartForConditionalGeneration, BartTokenizer
model = BartForConditionalGeneration.from_pretrained("facebook/bart-large", forced_bos_token_id=0)
tok = BartTokenizer.from_pretrained("facebook/bart-large")
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
( 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 )
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 theinputs_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
orfunction
, 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 truncatednormal_initializer for initializing all weight matrices. encoder_layerdrop — (float
, _optional, defaults to 0.0): The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. decoderlayerdrop — (float
, _optional, defaults to 0.0): The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. -
scale_embedding (
bool
, optional, defaults toFalse
) — Scale embeddings by diving by sqrt(d_model). -
use_cache (
bool
, optional, defaults toTrue
) — Whether or not the model should return the last key/values attentions (not used by all models). numlabels — (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 whenmax_length
is reached. Usually set toeos_token_id
.
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.
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
( 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 )
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
( 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 )
Construct a βfastβ BART tokenizer (backed by HuggingFaceβs tokenizers library).
BartTokenizerFast is identical to RobertaTokenizerFast. Refer to superclass RobertaTokenizerFast for usage examples and documentation concerning the initialization parameters and other methods.
BartModel
( config: BartConfig )
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.
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.
(
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
)
β
Seq2SeqModelOutput or tuple(torch.FloatTensor)
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.
-
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.
Bart uses the
eos_token_id
as the starting token fordecoder_input_ids
generation. Ifpast_key_values
is used, optionally only the lastdecoder_input_ids
have to be input (seepast_key_values
).For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 lastdecoder_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
(batchsize, sequence_length). - **inputs_embeds** (
torch.FloatTensorof shape
(batch_size, sequence_length, hidden_size)`, _optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_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 passingdecoder_input_ids
you can choose to directly pass an embedded representation. Ifpast_key_values
is used, optionally only the lastdecoder_inputs_embeds
have to be input (seepast_key_values
). This is useful if you want more control over how to convertdecoder_input_ids
indices into associated vectors than the model’s internal embedding lookup matrix.If
decoder_input_ids
anddecoder_inputs_embeds
are both unset,decoder_inputs_embeds
takes the value ofinputs_embeds
. -
use_cache (
bool
, optional) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
Seq2SeqModelOutput or tuple(torch.FloatTensor)
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)
) β 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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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.
The BartModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Example:
>>> from transformers import BartTokenizer, BartModel
>>> import torch
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> model = BartModel.from_pretrained('facebook/bart-large')
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
BartForConditionalGeneration
( config: BartConfig )
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.
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.
(
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
)
β
Seq2SeqLMOutput or tuple(torch.FloatTensor)
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.
-
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.
Bart uses the
eos_token_id
as the starting token fordecoder_input_ids
generation. Ifpast_key_values
is used, optionally only the lastdecoder_input_ids
have to be input (seepast_key_values
).For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 lastdecoder_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
(batchsize, sequence_length). - **inputs_embeds** (
torch.FloatTensorof shape
(batch_size, sequence_length, hidden_size)`, _optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_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 passingdecoder_input_ids
you can choose to directly pass an embedded representation. Ifpast_key_values
is used, optionally only the lastdecoder_inputs_embeds
have to be input (seepast_key_values
). This is useful if you want more control over how to convertdecoder_input_ids
indices into associated vectors than the model’s internal embedding lookup matrix.If
decoder_input_ids
anddecoder_inputs_embeds
are both unset,decoder_inputs_embeds
takes the value ofinputs_embeds
. -
use_cache (
bool
, optional) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_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 (seeinput_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
Seq2SeqLMOutput or tuple(torch.FloatTensor)
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 whenlabels
is provided) β Language modeling loss. -
logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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.
The BartForConditionalGeneration forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Summarization example:
>>> from transformers import BartTokenizer, BartForConditionalGeneration, BartConfig
>>> model = BartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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])
Mask filling example:
>>> from transformers import BartTokenizer, BartForConditionalGeneration
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> TXT = "My friends are <mask> but they eat too many carbs."
>>> model = BartForConditionalGeneration.from_pretrained('facebook/bart-large')
>>> input_ids = tokenizer([TXT], return_tensors='pt')['input_ids']
>>> logits = model(input_ids).logits
>>> masked_index = (input_ids[0] == tokenizer.mask_token_id).nonzero().item()
>>> probs = logits[0, masked_index].softmax(dim=0)
>>> values, predictions = probs.topk(5)
>>> tokenizer.decode(predictions).split()
BartForSequenceClassification
( config: BartConfig **kwargs )
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.
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.
(
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
)
β
Seq2SeqSequenceClassifierOutput or tuple(torch.FloatTensor)
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.
-
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.
Bart uses the
eos_token_id
as the starting token fordecoder_input_ids
generation. Ifpast_key_values
is used, optionally only the lastdecoder_input_ids
have to be input (seepast_key_values
).For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 lastdecoder_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
(batchsize, sequence_length). - **inputs_embeds** (
torch.FloatTensorof shape
(batch_size, sequence_length, hidden_size)`, _optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_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 passingdecoder_input_ids
you can choose to directly pass an embedded representation. Ifpast_key_values
is used, optionally only the lastdecoder_inputs_embeds
have to be input (seepast_key_values
). This is useful if you want more control over how to convertdecoder_input_ids
indices into associated vectors than the model’s internal embedding lookup matrix.If
decoder_input_ids
anddecoder_inputs_embeds
are both unset,decoder_inputs_embeds
takes the value ofinputs_embeds
. -
use_cache (
bool
, optional) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_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]
. Ifconfig.num_labels > 1
a classification loss is computed (Cross-Entropy).
Returns
Seq2SeqSequenceClassifierOutput or tuple(torch.FloatTensor)
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 whenlabel
is provided) β Classification (or regression if config.num_labels==1) loss. -
logits (
torch.FloatTensor
of shape(batch_size, config.num_labels)
) β Classification (or regression if config.num_labels==1) scores (before SoftMax). -
past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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.
The BartForSequenceClassification forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Example of single-label classification:
>>> from transformers import BartTokenizer, BartForSequenceClassification
>>> import torch
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> model = BartForSequenceClassification.from_pretrained('facebook/bart-large')
>>> 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
Example of multi-label classification:
>>> from transformers import BartTokenizer, BartForSequenceClassification
>>> import torch
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> model = BartForSequenceClassification.from_pretrained('facebook/bart-large', problem_type="multi_label_classification")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> labels = torch.tensor([[1, 1]], dtype=torch.float) # need dtype=float for BCEWithLogitsLoss
>>> outputs = model(**inputs, labels=labels)
>>> loss = outputs.loss
>>> logits = outputs.logits
BartForQuestionAnswering
( config )
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.
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.
(
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
)
β
Seq2SeqQuestionAnsweringModelOutput or tuple(torch.FloatTensor)
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.
-
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.
Bart uses the
eos_token_id
as the starting token fordecoder_input_ids
generation. Ifpast_key_values
is used, optionally only the lastdecoder_input_ids
have to be input (seepast_key_values
).For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 lastdecoder_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
(batchsize, sequence_length). - **inputs_embeds** (
torch.FloatTensorof shape
(batch_size, sequence_length, hidden_size)`, _optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_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 passingdecoder_input_ids
you can choose to directly pass an embedded representation. Ifpast_key_values
is used, optionally only the lastdecoder_inputs_embeds
have to be input (seepast_key_values
). This is useful if you want more control over how to convertdecoder_input_ids
indices into associated vectors than the model’s internal embedding lookup matrix.If
decoder_input_ids
anddecoder_inputs_embeds
are both unset,decoder_inputs_embeds
takes the value ofinputs_embeds
. -
use_cache (
bool
, optional) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_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
Seq2SeqQuestionAnsweringModelOutput or tuple(torch.FloatTensor)
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 whenlabels
is provided) β 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)
) β Span-start scores (before SoftMax). -
end_logits (
torch.FloatTensor
of shape(batch_size, sequence_length)
) β Span-end scores (before SoftMax). -
past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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.
The BartForQuestionAnswering forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Example:
>>> from transformers import BartTokenizer, BartForQuestionAnswering
>>> import torch
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> model = BartForQuestionAnswering.from_pretrained('facebook/bart-large')
>>> 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
(
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
)
β
CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
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.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple oftuple(torch.FloatTensor)
of lengthconfig.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 lastdecoder_input_ids
(those that don’t have their past key value states given to this model) of shape(batch_size, 1)
instead of alldecoder_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 (seeinput_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 toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
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 whenlabels
is provided) β Language modeling loss (for next-token prediction). -
logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftorch.FloatTensor
tuples of lengthconfig.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 ifconfig.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
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> model = BartForCausalLM.from_pretrained('facebook/bart-large', add_cross_attention=False)
>>> 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)
>>> logits = outputs.logits
TFBartModel
( *args **kwargs )
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.
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.
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])
ormodel([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})
(
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: typing.Union[typing.Tuple, transformers.modeling_tf_outputs.TFBaseModelOutput, NoneType] = 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
)
β
TFSeq2SeqModelOutput or tuple(tf.Tensor)
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.
-
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.
Bart uses the
eos_token_id
as the starting token fordecoder_input_ids
generation. Ifpast_key_values
is used, optionally only the lastdecoder_input_ids
have to be input (seepast_key_values
).For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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 lengthconfig.n_layers
) — contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. Ifpast_key_values
are used, the user can optionally input only the lastdecoder_input_ids
(those that don’t have their past key value states given to this model) of shape(batch_size, 1)
instead of alldecoder_input_ids
of shape(batch_size, sequence_length)
. -
use_cache (
bool
, optional, defaults toTrue
) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). Set toFalse
during training,True
during generation -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
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. Seehidden_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 toFalse
) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
Returns
TFSeq2SeqModelOutput or tuple(tf.Tensor)
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)
) β 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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) β List oftf.Tensor
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftf.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftf.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftf.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftf.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.
The TFBartModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Example:
>>> from transformers import BartTokenizer, TFBartModel
>>> import tensorflow as tf
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> model = TFBartModel.from_pretrained('facebook/bart-large')
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> outputs = model(inputs)
>>> last_hidden_states = outputs.last_hidden_state
TFBartForConditionalGeneration
( *args **kwargs )
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.
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.
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])
ormodel([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})
(
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: typing.Optional[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
labels = None
training = False
**kwargs
)
β
TFSeq2SeqLMOutput or tuple(tf.Tensor)
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.
-
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.
Bart uses the
eos_token_id
as the starting token fordecoder_input_ids
generation. Ifpast_key_values
is used, optionally only the lastdecoder_input_ids
have to be input (seepast_key_values
).For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
-
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 lengthconfig.n_layers
) — contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. Ifpast_key_values
are used, the user can optionally input only the lastdecoder_input_ids
(those that don’t have their past key value states given to this model) of shape(batch_size, 1)
instead of alldecoder_input_ids
of shape(batch_size, sequence_length)
. -
use_cache (
bool
, optional, defaults toTrue
) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). Set toFalse
during training,True
during generation -
output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
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. Seehidden_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 toFalse
) — 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 (seeinput_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
TFSeq2SeqLMOutput or tuple(tf.Tensor)
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 whenlabels
is provided) β Language modeling loss. -
logits (
tf.Tensor
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
past_key_values (
List[tf.Tensor]
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β List oftf.Tensor
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftf.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftf.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftf.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftf.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.
The TFBartForConditionalGeneration forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Summarization example:
>>> from transformers import BartTokenizer, TFBartForConditionalGeneration, BartConfig
>>> model = TFBartForConditionalGeneration.from_pretrained('facebook/bart-large')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> 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])
Mask filling example:
>>> from transformers import BartTokenizer, TFBartForConditionalGeneration
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> TXT = "My friends are <mask> but they eat too many carbs."
>>> model = TFBartForConditionalGeneration.from_pretrained('facebook/bart-large')
>>> 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
( config: BartConfig input_shape: typing.Tuple[int] = (1, 1) seed: int = 0 dtype: dtype = <class 'jax._src.numpy.lax_numpy.float32'> **kwargs )
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.
-
dtype (
jax.numpy.dtype
, optional, defaults tojax.numpy.float32
) — The data type of the computation. Can be one ofjax.numpy.float32
,jax.numpy.float16
(on GPUs) andjax.numpy.bfloat16
(on TPUs).This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given
dtype
.Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.
If you wish to change the dtype of the model parameters, see to_fp16() and to_bf16().
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:
(
input_ids: ndarray
attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_input_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxSeq2SeqModelOutput or tuple(torch.FloatTensor)
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.
-
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.
For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxSeq2SeqModelOutput or tuple(torch.FloatTensor)
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)
) β 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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(jnp.ndarray)
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.ndarray
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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.
The FlaxBartPreTrainedModel
forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Example:
>>> from transformers import BartTokenizer, FlaxBartModel
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-base')
>>> model = FlaxBartModel.from_pretrained('facebook/bart-base')
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors='jax')
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
(
input_ids: ndarray
attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxBaseModelOutput or tuple(torch.FloatTensor)
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.
-
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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxBaseModelOutput or tuple(torch.FloatTensor)
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 (BartConfig'>
) and inputs.
-
last_hidden_state (
jnp.ndarray
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model. -
hidden_states (
tuple(jnp.ndarray)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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_input_ids
encoder_outputs
encoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
past_key_values: dict = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
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.
For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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 byinit_cache
or when passing previouspast_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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
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 (BartConfig'>
) and inputs.
-
last_hidden_state (
jnp.ndarray
of shape(batch_size, sequence_length, hidden_size)
) β 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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(jnp.ndarray)
of lengthconfig.n_layers
, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)
) and optionally ifconfig.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 (seepast_key_values
input) to speed up sequential decoding. -
hidden_states (
tuple(jnp.ndarray)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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 whenoutput_attentions=True
andconfig.add_cross_attention=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.ndarray
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
Example:
>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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
FlaxBartForConditionalGeneration
( config: BartConfig input_shape: typing.Tuple[int] = (1, 1) seed: int = 0 dtype: dtype = <class 'jax._src.numpy.lax_numpy.float32'> **kwargs )
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.
-
dtype (
jax.numpy.dtype
, optional, defaults tojax.numpy.float32
) — The data type of the computation. Can be one ofjax.numpy.float32
,jax.numpy.float16
(on GPUs) andjax.numpy.bfloat16
(on TPUs).This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given
dtype
.Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.
If you wish to change the dtype of the model parameters, see to_fp16() and to_bf16().
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:
(
input_ids: ndarray
attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_input_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxSeq2SeqLMOutput or tuple(torch.FloatTensor)
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.
-
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.
For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxSeq2SeqLMOutput or tuple(torch.FloatTensor)
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)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
past_key_values (
tuple(tuple(jnp.ndarray))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(jnp.ndarray)
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.ndarray
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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.
The FlaxBartPreTrainedModel
forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Summarization example:
>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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))
Mask filling example:
>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
>>> TXT = "My friends are <mask> but they eat too many carbs."
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large')
>>> input_ids = tokenizer([TXT], return_tensors='jax')['input_ids']
>>> logits = model(input_ids).logits
>>> masked_index = (input_ids[0] == tokenizer.mask_token_id).nonzero()[0].item()
>>> probs = jax.nn.softmax(logits[0, masked_index], axis=0)
>>> values, predictions = jax.lax.top_k(probs)
>>> tokenizer.decode(predictions).split()
(
input_ids: ndarray
attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxBaseModelOutput or tuple(torch.FloatTensor)
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.
-
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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxBaseModelOutput or tuple(torch.FloatTensor)
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 (BartConfig'>
) and inputs.
-
last_hidden_state (
jnp.ndarray
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model. -
hidden_states (
tuple(jnp.ndarray)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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_input_ids
encoder_outputs
encoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
past_key_values: dict = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxCausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
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.
For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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 byinit_cache
or when passing previouspast_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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxCausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
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 (BartConfig'>
) and inputs.
-
logits (
jnp.ndarray
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
hidden_states (
tuple(jnp.ndarray)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple ofjnp.ndarray
tuples of lengthconfig.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 ifconfig.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
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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
FlaxBartForSequenceClassification
( config: BartConfig input_shape: typing.Tuple[int] = (1, 1) seed: int = 0 dtype: dtype = <class 'jax._src.numpy.lax_numpy.float32'> **kwargs )
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.
-
dtype (
jax.numpy.dtype
, optional, defaults tojax.numpy.float32
) — The data type of the computation. Can be one ofjax.numpy.float32
,jax.numpy.float16
(on GPUs) andjax.numpy.bfloat16
(on TPUs).This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given
dtype
.Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.
If you wish to change the dtype of the model parameters, see to_fp16() and to_bf16().
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:
(
input_ids: ndarray
attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_input_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxSeq2SeqSequenceClassifierOutput or tuple(torch.FloatTensor)
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.
-
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.
For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxSeq2SeqSequenceClassifierOutput or tuple(torch.FloatTensor)
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)
) β Classification (or regression if config.num_labels==1) scores (before SoftMax). -
past_key_values (
tuple(tuple(jnp.ndarray))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(jnp.ndarray)
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.ndarray
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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.
The FlaxBartPreTrainedModel
forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Example:
>>> from transformers import BartTokenizer, FlaxBartForSequenceClassification
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-base')
>>> model = FlaxBartForSequenceClassification.from_pretrained('facebook/bart-base')
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors='jax')
>>> outputs = model(**inputs)
>>> logits = outputs.logits
(
input_ids: ndarray
attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxBaseModelOutput or tuple(torch.FloatTensor)
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.
-
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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxBaseModelOutput or tuple(torch.FloatTensor)
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 (BartConfig'>
) and inputs.
-
last_hidden_state (
jnp.ndarray
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model. -
hidden_states (
tuple(jnp.ndarray)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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_input_ids
encoder_outputs
encoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
past_key_values: dict = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
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.
For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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 byinit_cache
or when passing previouspast_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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
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 (BartConfig'>
) and inputs.
-
last_hidden_state (
jnp.ndarray
of shape(batch_size, sequence_length, hidden_size)
) β 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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(jnp.ndarray)
of lengthconfig.n_layers
, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)
) and optionally ifconfig.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 (seepast_key_values
input) to speed up sequential decoding. -
hidden_states (
tuple(jnp.ndarray)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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 whenoutput_attentions=True
andconfig.add_cross_attention=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.ndarray
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
Example:
>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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
FlaxBartForQuestionAnswering
( config: BartConfig input_shape: typing.Tuple[int] = (1, 1) seed: int = 0 dtype: dtype = <class 'jax._src.numpy.lax_numpy.float32'> **kwargs )
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.
-
dtype (
jax.numpy.dtype
, optional, defaults tojax.numpy.float32
) — The data type of the computation. Can be one ofjax.numpy.float32
,jax.numpy.float16
(on GPUs) andjax.numpy.bfloat16
(on TPUs).This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given
dtype
.Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.
If you wish to change the dtype of the model parameters, see to_fp16() and to_bf16().
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:
(
input_ids: ndarray
attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_input_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxSeq2SeqQuestionAnsweringModelOutput or tuple(torch.FloatTensor)
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.
-
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.
For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxSeq2SeqQuestionAnsweringModelOutput or tuple(torch.FloatTensor)
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)
) β Span-start scores (before SoftMax). -
end_logits (
jnp.ndarray
of shape(batch_size, sequence_length)
) β Span-end scores (before SoftMax). -
past_key_values (
tuple(tuple(jnp.ndarray))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(jnp.ndarray)
of lengthconfig.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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.ndarray
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs 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) β 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 whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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.
The FlaxBartPreTrainedModel
forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post
processing steps while the latter silently ignores them.
Example:
>>> from transformers import BartTokenizer, FlaxBartForQuestionAnswering
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-base')
>>> model = FlaxBartForQuestionAnswering.from_pretrained('facebook/bart-base')
>>> 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
(
input_ids: ndarray
attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxBaseModelOutput or tuple(torch.FloatTensor)
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.
-
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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxBaseModelOutput or tuple(torch.FloatTensor)
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 (BartConfig'>
) and inputs.
-
last_hidden_state (
jnp.ndarray
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model. -
hidden_states (
tuple(jnp.ndarray)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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_input_ids
encoder_outputs
encoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
decoder_position_ids: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None
past_key_values: dict = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
return_dict: typing.Optional[bool] = None
train: bool = False
params: dict = None
dropout_rng: PRNGKey = None
)
β
FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
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.
For translation and summarization training,
decoder_input_ids
should be provided. If nodecoder_input_ids
is provided, the model will create this tensor by shifting theinput_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 indecoder_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 byinit_cache
or when passing previouspast_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. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. -
return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
FlaxBaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
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 (BartConfig'>
) and inputs.
-
last_hidden_state (
jnp.ndarray
of shape(batch_size, sequence_length, hidden_size)
) β 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 whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(jnp.ndarray)
of lengthconfig.n_layers
, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)
) and optionally ifconfig.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 (seepast_key_values
input) to speed up sequential decoding. -
hidden_states (
tuple(jnp.ndarray)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple ofjnp.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 whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.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 whenoutput_attentions=True
andconfig.add_cross_attention=True
is passed or whenconfig.output_attentions=True
) β Tuple ofjnp.ndarray
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights of the decoderβs cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
Example:
>>> from transformers import BartTokenizer, FlaxBartForConditionalGeneration
>>> model = FlaxBartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
>>> tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
>>> 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