LED
Overview
The LED model was proposed in Longformer: The Long-Document Transformer by Iz Beltagy, Matthew E. Peters, Arman Cohan.
The abstract from the paper is the following:
Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism that scales linearly with sequence length, making it easy to process documents of thousands of tokens or longer. Longformer’s attention mechanism is a drop-in replacement for the standard self-attention and combines a local windowed attention with a task motivated global attention. Following prior work on long-sequence transformers, we evaluate Longformer on character-level language modeling and achieve state-of-the-art results on text8 and enwik8. In contrast to most prior work, we also pretrain Longformer and finetune it on a variety of downstream tasks. Our pretrained Longformer consistently outperforms RoBERTa on long document tasks and sets new state-of-the-art results on WikiHop and TriviaQA. We finally introduce the Longformer-Encoder-Decoder (LED), a Longformer variant for supporting long document generative sequence-to-sequence tasks, and demonstrate its effectiveness on the arXiv summarization dataset.
Usage tips
- LEDForConditionalGeneration is an extension of BartForConditionalGeneration exchanging the traditional self-attention layer with Longformer’s chunked self-attention layer. LEDTokenizer is an alias of BartTokenizer.
- LED works very well on long-range sequence-to-sequence tasks where the
input_idslargely exceed a length of 1024 tokens. - LED pads the
input_idsto be a multiple ofconfig.attention_windowif required. Therefore a small speed-up is gained, when LEDTokenizer is used with thepad_to_multiple_ofargument. - LED makes use of global attention by means of the
global_attention_mask(see LongformerModel). For summarization, it is advised to put global attention only on the first<s>token. For question answering, it is advised to put global attention on all tokens of the question. - To fine-tune LED on all 16384, gradient checkpointing can be enabled in case training leads to out-of-memory (OOM)
errors. This can be done by executing
model.gradient_checkpointing_enable(). Moreover, theuse_cache=Falseflag can be used to disable the caching mechanism to save memory. - LED is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.
This model was contributed by patrickvonplaten.
Resources
- A notebook showing how to evaluate LED.
- A notebook showing how to fine-tune LED.
- Text classification task guide
- Question answering task guide
- Translation task guide
- Summarization task guide
LEDConfig
class transformers.LEDConfig
< source >( vocab_size = 50265 max_encoder_position_embeddings = 16384 max_decoder_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 use_cache = True is_encoder_decoder = True activation_function = 'gelu' d_model = 1024 dropout = 0.1 attention_dropout = 0.0 activation_dropout = 0.0 init_std = 0.02 decoder_start_token_id = 2 classifier_dropout = 0.0 pad_token_id = 1 bos_token_id = 0 eos_token_id = 2 attention_window: typing.Union[typing.List[int], int] = 512 **kwargs )
Parameters
- vocab_size (
int, optional, defaults to 50265) — Vocabulary size of the LED model. Defines the number of different tokens that can be represented by theinputs_idspassed when calling LEDModel or TFLEDModel. - 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 (
strorfunction, 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_encoder_position_embeddings (
int, optional, defaults to 16384) — The maximum sequence length that the encoder might ever be used with. - max_decoder_position_embeddings (
int, optional, defaults to 16384) — The maximum sequence length that the decoder might ever be used with. - init_std (
float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. - encoder_layerdrop (
float, optional, defaults to 0.0) — The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. - decoder_layerdrop (
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. - use_cache (
bool, optional, defaults toTrue) — Whether or not the model should return the last key/values attentions (not used by all models)
This is the configuration class to store the configuration of a LEDModel. It is used to instantiate an LED 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 LED allenai/led-base-16384 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 LEDModel, LEDConfig
>>> # Initializing a LED allenai/led-base-16384 style configuration
>>> configuration = LEDConfig()
>>> # Initializing a model from the allenai/led-base-16384 style configuration
>>> model = LEDModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.configLEDTokenizer
class transformers.LEDTokenizer
< source >( 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 )
Parameters
- vocab_file (
str) — Path to the vocabulary file. - merges_file (
str) — Path to the merges file. - errors (
str, optional, defaults to"replace") — Paradigm to follow when decoding bytes to UTF-8. See bytes.decode for more information. - bos_token (
str, optional, defaults to"<s>") — The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.When building a sequence using special tokens, this is not the token that is used for the beginning of sequence. The token used is the
cls_token. - eos_token (
str, optional, defaults to"</s>") — The end of sequence token.When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the
sep_token. - sep_token (
str, optional, defaults to"</s>") — The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens. - cls_token (
str, optional, defaults to"<s>") — The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens. - unk_token (
str, optional, defaults to"<unk>") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead. - pad_token (
str, optional, defaults to"<pad>") — The token used for padding, for example when batching sequences of different lengths. - mask_token (
str, optional, defaults to"<mask>") — The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict. - add_prefix_space (
bool, optional, defaults toFalse) — Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (BART tokenizer detect beginning of words by the preceding space).
Constructs a LED tokenizer, which is smilar to the ROBERTa tokenizer, using byte-level Byte-Pair-Encoding.
This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
be encoded differently whether it is at the beginning of the sentence (without space) or not:
>>> from transformers import LEDTokenizer
>>> tokenizer = LEDTokenizer.from_pretrained("allenai/led-base-16384")
>>> tokenizer("Hello world")["input_ids"]
[0, 31414, 232, 2]
>>> tokenizer(" Hello world")["input_ids"]
[0, 20920, 232, 2]You can get around that behavior by passing add_prefix_space=True when instantiating this tokenizer or when you
call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.
When used with is_split_into_words=True, this tokenizer will add a space before each word (even the first one).
This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.
build_inputs_with_special_tokens
< source >( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) → List[int]
Parameters
- token_ids_0 (
List[int]) — List of IDs to which the special tokens will be added. - token_ids_1 (
List[int], optional) — Optional second list of IDs for sequence pairs.
Returns
List[int]
List of input IDs with the appropriate special tokens.
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A LED sequence has the following format:
- single sequence:
<s> X </s> - pair of sequences:
<s> A </s></s> B </s>
get_special_tokens_mask
< source >( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None already_has_special_tokens: bool = False ) → List[int]
Parameters
- token_ids_0 (
List[int]) — List of IDs. - token_ids_1 (
List[int], optional) — Optional second list of IDs for sequence pairs. - already_has_special_tokens (
bool, optional, defaults toFalse) — Whether or not the token list is already formatted with special tokens for the model.
Returns
List[int]
A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer prepare_for_model method.
create_token_type_ids_from_sequences
< source >( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) → List[int]
Create a mask from the two sequences passed to be used in a sequence-pair classification task. LED does not make use of token type ids, therefore a list of zeros is returned.
LEDTokenizerFast
class transformers.LEDTokenizerFast
< source >( 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 trim_offsets = True **kwargs )
Parameters
- vocab_file (
str) — Path to the vocabulary file. - merges_file (
str) — Path to the merges file. - errors (
str, optional, defaults to"replace") — Paradigm to follow when decoding bytes to UTF-8. See bytes.decode for more information. - bos_token (
str, optional, defaults to"<s>") — The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.When building a sequence using special tokens, this is not the token that is used for the beginning of sequence. The token used is the
cls_token. - eos_token (
str, optional, defaults to"</s>") — The end of sequence token.When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the
sep_token. - sep_token (
str, optional, defaults to"</s>") — The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens. - cls_token (
str, optional, defaults to"<s>") — The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens. - unk_token (
str, optional, defaults to"<unk>") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead. - pad_token (
str, optional, defaults to"<pad>") — The token used for padding, for example when batching sequences of different lengths. - mask_token (
str, optional, defaults to"<mask>") — The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict. - add_prefix_space (
bool, optional, defaults toFalse) — Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (LED tokenizer detect beginning of words by the preceding space). - trim_offsets (
bool, optional, defaults toTrue) — Whether the post processing step should trim offsets to avoid including whitespaces.
Construct a “fast” LED tokenizer (backed by HuggingFace’s tokenizers library), derived from the GPT-2 tokenizer, using byte-level Byte-Pair-Encoding.
This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
be encoded differently whether it is at the beginning of the sentence (without space) or not:
>>> from transformers import LEDTokenizerFast
>>> tokenizer = LEDTokenizerFast.from_pretrained("allenai/led-base-16384")
>>> tokenizer("Hello world")["input_ids"]
[0, 31414, 232, 2]
>>> tokenizer(" Hello world")["input_ids"]
[0, 20920, 232, 2]You can get around that behavior by passing add_prefix_space=True when instantiating this tokenizer or when you
call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.
When used with is_split_into_words=True, this tokenizer needs to be instantiated with add_prefix_space=True.
This tokenizer inherits from PreTrainedTokenizerFast which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.
create_token_type_ids_from_sequences
< source >( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) → List[int]
Create a mask from the two sequences passed to be used in a sequence-pair classification task. LED does not make use of token type ids, therefore a list of zeros is returned.
LED specific outputs
class transformers.models.led.modeling_led.LEDEncoderBaseModelOutput
< source >( last_hidden_state: FloatTensor hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None global_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )
Parameters
- last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model. - hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x + attention_window + 1), wherexis the number of tokens with global attention mask.Local attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token in the sequence to every token with global attention (first
xvalues) and to every token in the attention window (remaining `attention_window- 1
values). Note that the firstxvalues refer to tokens with fixed positions in the text, but the remainingattention_window + 1values refer to tokens with relative positions: the attention weight of a token to itself is located at indexx + attention_window / 2and theattention_window / 2preceding (succeeding) values are the attention weights to theattention_window / 2preceding (succeeding) tokens. If the attention window contains a token with global attention, the attention weight at the corresponding index is set to 0; the value should be accessed from the firstxattention weights. If a token has global attention, the attention weights to all other tokens inattentionsis set to 0, the values should be accessed fromglobal_attentions`.
- 1
- global_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
Base class for LEDEncoder’s outputs, with potential hidden states, local and global attentions.
class transformers.models.led.modeling_led.LEDSeq2SeqModelOutput
< source >( last_hidden_state: FloatTensor = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_global_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )
Parameters
- last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the decoder of the model.If
past_key_valuesis used only the last hidden-state of the sequences of shape(batch_size, 1, hidden_size)is output. - past_key_values (
List[torch.FloatTensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftorch.FloatTensorof 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_valuesinput) to speed up sequential decoding. - decoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
- encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. - encoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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.
- encoder_global_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
Base class for model encoder’s outputs that also contains : pre-computed hidden states that can speed up sequential decoding.
class transformers.models.led.modeling_led.LEDSeq2SeqLMOutput
< source >( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_global_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )
Parameters
- loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. - logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - past_key_values (
List[torch.FloatTensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftorch.FloatTensorof 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_valuesinput) to speed up sequential decoding. - decoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
- encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. - encoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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.
- encoder_global_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
Base class for sequence-to-sequence language models outputs.
class transformers.models.led.modeling_led.LEDSeq2SeqSequenceClassifierOutput
< source >( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_global_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )
Parameters
- loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelis provided) — Classification (or regression if config.num_labels==1) loss. - logits (
torch.FloatTensorof shape(batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax). - past_key_values (
List[torch.FloatTensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftorch.FloatTensorof 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_valuesinput) to speed up sequential decoding. - decoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
- encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. - encoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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.
- encoder_global_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
Base class for outputs of sequence-to-sequence sentence classification models.
class transformers.models.led.modeling_led.LEDSeq2SeqQuestionAnsweringModelOutput
< source >( loss: typing.Optional[torch.FloatTensor] = None start_logits: FloatTensor = None end_logits: FloatTensor = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None decoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None decoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None encoder_global_attentions: typing.Optional[typing.Tuple[torch.FloatTensor, ...]] = None )
Parameters
- loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Total span extraction loss is the sum of a Cross-Entropy for the start and end positions. - start_logits (
torch.FloatTensorof shape(batch_size, sequence_length)) — Span-start scores (before SoftMax). - end_logits (
torch.FloatTensorof shape(batch_size, sequence_length)) — Span-end scores (before SoftMax). - past_key_values (
List[torch.FloatTensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftorch.FloatTensorof 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_valuesinput) to speed up sequential decoding. - decoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
- encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. - encoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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.
- encoder_global_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
Base class for outputs of sequence-to-sequence question answering models.
class transformers.models.led.modeling_tf_led.TFLEDEncoderBaseModelOutput
< source >( last_hidden_state: tf.Tensor = None hidden_states: Tuple[tf.Tensor, ...] | None = None attentions: Tuple[tf.Tensor, ...] | None = None global_attentions: Tuple[tf.Tensor, ...] | None = None )
Parameters
- last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model. - hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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 model at the output of each layer plus the initial embedding outputs.
- attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x + attention_window + 1), wherexis the number of tokens with global attention mask.Local attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token in the sequence to every token with global attention (first
xvalues) and to every token in the attention window (remaining `attention_window- 1
values). Note that the firstxvalues refer to tokens with fixed positions in the text, but the remainingattention_window + 1values refer to tokens with relative positions: the attention weight of a token to itself is located at indexx + attention_window / 2and theattention_window / 2preceding (succeeding) values are the attention weights to theattention_window / 2preceding (succeeding) tokens. If the attention window contains a token with global attention, the attention weight at the corresponding index is set to 0; the value should be accessed from the firstxattention weights. If a token has global attention, the attention weights to all other tokens inattentionsis set to 0, the values should be accessed fromglobal_attentions`.
- 1
- global_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
Base class for Longformer’s outputs, with potential hidden states, local and global attentions.
class transformers.models.led.modeling_tf_led.TFLEDSeq2SeqModelOutput
< source >( last_hidden_state: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None decoder_hidden_states: Tuple[tf.Tensor, ...] | None = None decoder_attentions: Tuple[tf.Tensor, ...] | None = None cross_attentions: Tuple[tf.Tensor, ...] | None = None encoder_last_hidden_state: tf.Tensor | None = None encoder_hidden_states: Tuple[tf.Tensor, ...] | None = None encoder_attentions: Tuple[tf.Tensor, ...] | None = None encoder_global_attentions: Tuple[tf.Tensor, ...] | None = None )
Parameters
- last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the decoder of the model.If
past_key_valuesis 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=Trueis passed or whenconfig.use_cache=True) — List oftf.Tensorof 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_valuesinput) to speed up sequential decoding. - decoder_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
- encoder_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. - encoder_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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.
- encoder_global_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
Base class for model encoder’s outputs that also contains : pre-computed hidden states that can speed up sequential decoding.
class transformers.models.led.modeling_tf_led.TFLEDSeq2SeqLMOutput
< source >( loss: tf.Tensor | None = None logits: tf.Tensor = None past_key_values: List[tf.Tensor] | None = None decoder_hidden_states: Tuple[tf.Tensor, ...] | None = None decoder_attentions: Tuple[tf.Tensor, ...] | None = None cross_attentions: Tuple[tf.Tensor, ...] | None = None encoder_last_hidden_state: tf.Tensor | None = None encoder_hidden_states: Tuple[tf.Tensor, ...] | None = None encoder_attentions: Tuple[tf.Tensor, ...] | None = None encoder_global_attentions: Tuple[tf.Tensor, ...] | None = None )
Parameters
- loss (
tf.Tensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. - logits (
tf.Tensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - past_key_values (
List[tf.Tensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftf.Tensorof 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_valuesinput) to speed up sequential decoding. - decoder_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
- encoder_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. - encoder_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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.
- encoder_global_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
Base class for sequence-to-sequence language models outputs.
LEDModel
class transformers.LEDModel
< source >( config: LEDConfig )
Parameters
- config (LEDConfig) — 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 LED Model outputting raw hidden-states without any specific head on top. This model inherits from PreTrainedModel. See the superclass documentation for the generic methods the library implements for all its models (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 general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None decoder_input_ids: typing.Optional[torch.LongTensor] = None decoder_attention_mask: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.Tensor] = None decoder_head_mask: typing.Optional[torch.Tensor] = None cross_attn_head_mask: typing.Optional[torch.Tensor] = None encoder_outputs: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None global_attention_mask: typing.Optional[torch.FloatTensor] = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None decoder_inputs_embeds: typing.Optional[torch.FloatTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.Seq2SeqModelOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof 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 AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.Tensorof 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.LongTensorof shape(batch_size, target_sequence_length), optional) — Indices of decoder input sequence tokens in the vocabulary.Indices can be obtained using
LedTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.LED uses the
eos_token_idas the starting token fordecoder_input_idsgeneration. Ifpast_key_valuesis used, optionally only the lastdecoder_input_idshave to be input (seepast_key_values). - decoder_attention_mask (
torch.LongTensorof 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_led._prepare_decoder_inputsand modify to your needs. See diagram 1 in the paper for more information on the default strategy. - global_attention_mask (
torch.FloatTensorof shape(batch_size, sequence_length), optional) — Mask to decide the attention given on each token, local attention or global attention for the encoder. Tokens with global attention attends to all other tokens, and all other tokens attend to them. This is important for task-specific finetuning because it makes the model more flexible at representing the task. For example, for classification, thetoken should be given global attention. For QA, all question tokens should also have global attention. Please refer to the Longformer paper for more details. Mask values selected in[0, 1]:- 0 for local attention (a sliding window attention),
- 1 for global attention (tokens that attend to all other tokens, and all other tokens attend to them).
- head_mask (
torch.Tensorof 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.Tensorof 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.Tensorof 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_stateof 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=Trueis 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_valuesinput) to speed up sequential decoding.If
past_key_valuesare 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_idsof shape(batch_size, sequence_length). - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - decoder_inputs_embeds (
torch.FloatTensorof shape(batch_size, target_sequence_length, hidden_size), optional) — Optionally, instead of passingdecoder_input_idsyou can choose to directly pass an embedded representation. Ifpast_key_valuesis used, optionally only the lastdecoder_inputs_embedshave to be input (seepast_key_values). This is useful if you want more control over how to convertdecoder_input_idsindices into associated vectors than the model’s internal embedding lookup matrix.If
decoder_input_idsanddecoder_inputs_embedsare both unset,decoder_inputs_embedstakes the value ofinputs_embeds. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey 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. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_outputs.Seq2SeqModelOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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 (LEDConfig) and inputs.
-
last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the decoder of the model.If
past_key_valuesis 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=Trueis 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_valuesinput) to speed up sequential decoding. -
decoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden-states of the decoder at the output of each layer plus the optional initial embedding outputs.
-
decoder_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
-
encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. -
encoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden-states of the encoder at the output of each layer plus the optional initial embedding outputs.
-
encoder_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — 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 LEDModel 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 AutoTokenizer, LEDModel
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("allenai/led-base-16384")
>>> model = LEDModel.from_pretrained("allenai/led-base-16384")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_stateLEDForConditionalGeneration
class transformers.LEDForConditionalGeneration
< source >( config: LEDConfig )
Parameters
- config (LEDConfig) — 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 LED Model with a language modeling head. Can be used for summarization. This model inherits from PreTrainedModel. See the superclass documentation for the generic methods the library implements for all its models (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 general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None decoder_input_ids: typing.Optional[torch.LongTensor] = None decoder_attention_mask: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.Tensor] = None decoder_head_mask: typing.Optional[torch.Tensor] = None cross_attn_head_mask: typing.Optional[torch.Tensor] = None encoder_outputs: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None global_attention_mask: typing.Optional[torch.FloatTensor] = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None decoder_inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.Seq2SeqLMOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof 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 AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.Tensorof 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.LongTensorof shape(batch_size, target_sequence_length), optional) — Indices of decoder input sequence tokens in the vocabulary.Indices can be obtained using
LedTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.LED uses the
eos_token_idas the starting token fordecoder_input_idsgeneration. Ifpast_key_valuesis used, optionally only the lastdecoder_input_idshave to be input (seepast_key_values). - decoder_attention_mask (
torch.LongTensorof 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_led._prepare_decoder_inputsand modify to your needs. See diagram 1 in the paper for more information on the default strategy. - global_attention_mask (
torch.FloatTensorof shape(batch_size, sequence_length), optional) — Mask to decide the attention given on each token, local attention or global attention for the encoder. Tokens with global attention attends to all other tokens, and all other tokens attend to them. This is important for task-specific finetuning because it makes the model more flexible at representing the task. For example, for classification, thetoken should be given global attention. For QA, all question tokens should also have global attention. Please refer to the Longformer paper for more details. Mask values selected in[0, 1]:- 0 for local attention (a sliding window attention),
- 1 for global attention (tokens that attend to all other tokens, and all other tokens attend to them).
- head_mask (
torch.Tensorof 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.Tensorof 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.Tensorof 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_stateof 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=Trueis 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_valuesinput) to speed up sequential decoding.If
past_key_valuesare 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_idsof shape(batch_size, sequence_length). - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - decoder_inputs_embeds (
torch.FloatTensorof shape(batch_size, target_sequence_length, hidden_size), optional) — Optionally, instead of passingdecoder_input_idsyou can choose to directly pass an embedded representation. Ifpast_key_valuesis used, optionally only the lastdecoder_inputs_embedshave to be input (seepast_key_values). This is useful if you want more control over how to convertdecoder_input_idsindices into associated vectors than the model’s internal embedding lookup matrix.If
decoder_input_idsanddecoder_inputs_embedsare both unset,decoder_inputs_embedstakes the value ofinputs_embeds. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey 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. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof 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_idsdocstring). Tokens with indices set to-100are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size].
Returns
transformers.modeling_outputs.Seq2SeqLMOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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 (LEDConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. -
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
past_key_values (
tuple(tuple(torch.FloatTensor)), optional, returned whenuse_cache=Trueis 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_valuesinput) to speed up sequential decoding. -
decoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
-
decoder_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
-
encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. -
encoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
-
encoder_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — 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 LEDForConditionalGeneration 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.
Conditional generation example:
>>> from transformers import AutoTokenizer, LEDForConditionalGeneration
>>> tokenizer = AutoTokenizer.from_pretrained("allenai/led-base-16384")
>>> TXT = "My friends are <mask> but they eat too many carbs."
>>> model = LEDForConditionalGeneration.from_pretrained("allenai/led-base-16384")
>>> input_ids = tokenizer([TXT], return_tensors="pt")["input_ids"]
>>> prediction = model.generate(input_ids)[0]
>>> print(tokenizer.decode(prediction, skip_special_tokens=True))Summarization example:
>>> import torch
>>> from transformers import AutoTokenizer, LEDForConditionalGeneration
>>> model = LEDForConditionalGeneration.from_pretrained("allenai/led-large-16384-arxiv")
>>> tokenizer = AutoTokenizer.from_pretrained("allenai/led-large-16384-arxiv")
>>> ARTICLE_TO_SUMMARIZE = '''Transformers (Vaswani et al., 2017) have achieved state-of-the-art
... results in a wide range of natural language tasks including generative language modeling
... (Dai et al., 2019; Radford et al., 2019) and discriminative ... language understanding (Devlin et al., 2019).
... This success is partly due to the self-attention component which enables the network to capture contextual
... information from the entire sequence. While powerful, the memory and computational requirements of
... self-attention grow quadratically with sequence length, making it infeasible (or very expensive) to
... process long sequences. To address this limitation, we present Longformer, a modified Transformer
... architecture with a self-attention operation that scales linearly with the sequence length, making it
... versatile for processing long documents (Fig 1). This is an advantage for natural language tasks such as
... long document classification, question answering (QA), and coreference resolution, where existing approaches
... partition or shorten the long context into smaller sequences that fall within the typical 512 token limit
... of BERT-style pretrained models. Such partitioning could potentially result in loss of important
... cross-partition information, and to mitigate this problem, existing methods often rely on complex
... architectures to address such interactions. On the other hand, our proposed Longformer is able to build
... contextual representations of the entire context using multiple layers of attention, reducing the need for
... task-specific architectures.'''
>>> inputs = tokenizer.encode(ARTICLE_TO_SUMMARIZE, return_tensors="pt")
>>> # Global attention on the first token (cf. Beltagy et al. 2020)
>>> global_attention_mask = torch.zeros_like(inputs)
>>> global_attention_mask[:, 0] = 1
>>> # Generate Summary
>>> summary_ids = model.generate(inputs, global_attention_mask=global_attention_mask, num_beams=3, max_length=32)
>>> print(tokenizer.decode(summary_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=True))LEDForSequenceClassification
class transformers.LEDForSequenceClassification
< source >( config: LEDConfig **kwargs )
Parameters
- config (LEDConfig) — 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.
LED 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. See the superclass documentation for the generic methods the library implements for all its models (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 general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None decoder_input_ids: typing.Optional[torch.LongTensor] = None decoder_attention_mask: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.Tensor] = None decoder_head_mask: typing.Optional[torch.Tensor] = None cross_attn_head_mask: typing.Optional[torch.Tensor] = None encoder_outputs: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None global_attention_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None decoder_inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof 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 AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.Tensorof 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.LongTensorof shape(batch_size, target_sequence_length), optional) — Indices of decoder input sequence tokens in the vocabulary.Indices can be obtained using
LedTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.LED uses the
eos_token_idas the starting token fordecoder_input_idsgeneration. Ifpast_key_valuesis used, optionally only the lastdecoder_input_idshave to be input (seepast_key_values). - decoder_attention_mask (
torch.LongTensorof 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_led._prepare_decoder_inputsand modify to your needs. See diagram 1 in the paper for more information on the default strategy. - global_attention_mask (
torch.FloatTensorof shape(batch_size, sequence_length), optional) — Mask to decide the attention given on each token, local attention or global attention for the encoder. Tokens with global attention attends to all other tokens, and all other tokens attend to them. This is important for task-specific finetuning because it makes the model more flexible at representing the task. For example, for classification, thetoken should be given global attention. For QA, all question tokens should also have global attention. Please refer to the Longformer paper for more details. Mask values selected in[0, 1]:- 0 for local attention (a sliding window attention),
- 1 for global attention (tokens that attend to all other tokens, and all other tokens attend to them).
- head_mask (
torch.Tensorof 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.Tensorof 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.Tensorof 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_stateof 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=Trueis 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_valuesinput) to speed up sequential decoding.If
past_key_valuesare 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_idsof shape(batch_size, sequence_length). - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - decoder_inputs_embeds (
torch.FloatTensorof shape(batch_size, target_sequence_length, hidden_size), optional) — Optionally, instead of passingdecoder_input_idsyou can choose to directly pass an embedded representation. Ifpast_key_valuesis used, optionally only the lastdecoder_inputs_embedshave to be input (seepast_key_values). This is useful if you want more control over how to convertdecoder_input_idsindices into associated vectors than the model’s internal embedding lookup matrix.If
decoder_input_idsanddecoder_inputs_embedsare both unset,decoder_inputs_embedstakes the value ofinputs_embeds. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey 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. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof shape(batch_size,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]. Ifconfig.num_labels > 1a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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 (LEDConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelis provided) — Classification (or regression if config.num_labels==1) loss. -
logits (
torch.FloatTensorof shape(batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax). -
past_key_values (
tuple(tuple(torch.FloatTensor)), optional, returned whenuse_cache=Trueis 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_valuesinput) to speed up sequential decoding. -
decoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
-
decoder_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
-
encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. -
encoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
-
encoder_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — 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 LEDForSequenceClassification 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:
>>> import torch
>>> from transformers import AutoTokenizer, LEDForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("allenai/led-base-16384")
>>> model = LEDForSequenceClassification.from_pretrained("allenai/led-base-16384")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_class_id = logits.argmax().item()
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = LEDForSequenceClassification.from_pretrained("allenai/led-base-16384", num_labels=num_labels)
>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).lossExample of multi-label classification:
>>> import torch
>>> from transformers import AutoTokenizer, LEDForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("allenai/led-base-16384")
>>> model = LEDForSequenceClassification.from_pretrained("allenai/led-base-16384", problem_type="multi_label_classification")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = LEDForSequenceClassification.from_pretrained(
... "allenai/led-base-16384", num_labels=num_labels, problem_type="multi_label_classification"
... )
>>> labels = torch.sum(
... torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).lossLEDForQuestionAnswering
class transformers.LEDForQuestionAnswering
< source >( config )
Parameters
- config (LEDConfig) — 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.
LED 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. See the superclass documentation for the generic methods the library implements for all its models (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 general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None decoder_input_ids: typing.Optional[torch.LongTensor] = None decoder_attention_mask: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.Tensor] = None decoder_head_mask: typing.Optional[torch.Tensor] = None cross_attn_head_mask: typing.Optional[torch.Tensor] = None encoder_outputs: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None global_attention_mask: typing.Optional[torch.FloatTensor] = None start_positions: typing.Optional[torch.LongTensor] = None end_positions: typing.Optional[torch.LongTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None decoder_inputs_embeds: typing.Optional[torch.FloatTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof 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 AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.Tensorof 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.LongTensorof shape(batch_size, target_sequence_length), optional) — Indices of decoder input sequence tokens in the vocabulary.Indices can be obtained using
LedTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.LED uses the
eos_token_idas the starting token fordecoder_input_idsgeneration. Ifpast_key_valuesis used, optionally only the lastdecoder_input_idshave to be input (seepast_key_values). - decoder_attention_mask (
torch.LongTensorof 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_led._prepare_decoder_inputsand modify to your needs. See diagram 1 in the paper for more information on the default strategy. - global_attention_mask (
torch.FloatTensorof shape(batch_size, sequence_length), optional) — Mask to decide the attention given on each token, local attention or global attention for the encoder. Tokens with global attention attends to all other tokens, and all other tokens attend to them. This is important for task-specific finetuning because it makes the model more flexible at representing the task. For example, for classification, thetoken should be given global attention. For QA, all question tokens should also have global attention. Please refer to the Longformer paper for more details. Mask values selected in[0, 1]:- 0 for local attention (a sliding window attention),
- 1 for global attention (tokens that attend to all other tokens, and all other tokens attend to them).
- head_mask (
torch.Tensorof 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.Tensorof 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.Tensorof 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_stateof 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=Trueis 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_valuesinput) to speed up sequential decoding.If
past_key_valuesare 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_idsof shape(batch_size, sequence_length). - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - decoder_inputs_embeds (
torch.FloatTensorof shape(batch_size, target_sequence_length, hidden_size), optional) — Optionally, instead of passingdecoder_input_idsyou can choose to directly pass an embedded representation. Ifpast_key_valuesis used, optionally only the lastdecoder_inputs_embedshave to be input (seepast_key_values). This is useful if you want more control over how to convertdecoder_input_idsindices into associated vectors than the model’s internal embedding lookup matrix.If
decoder_input_idsanddecoder_inputs_embedsare both unset,decoder_inputs_embedstakes the value ofinputs_embeds. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey 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. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - start_positions (
torch.LongTensorof 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.LongTensorof 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
transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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 (LEDConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Total span extraction loss is the sum of a Cross-Entropy for the start and end positions. -
start_logits (
torch.FloatTensorof shape(batch_size, sequence_length)) — Span-start scores (before SoftMax). -
end_logits (
torch.FloatTensorof shape(batch_size, sequence_length)) — Span-end scores (before SoftMax). -
past_key_values (
tuple(tuple(torch.FloatTensor)), optional, returned whenuse_cache=Trueis 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_valuesinput) to speed up sequential decoding. -
decoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
-
decoder_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
-
encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. -
encoder_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
-
encoder_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — 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 LEDForQuestionAnswering 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 AutoTokenizer, LEDForQuestionAnswering
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("allenai/led-base-16384")
>>> model = LEDForQuestionAnswering.from_pretrained("allenai/led-base-16384")
>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
>>> inputs = tokenizer(question, text, return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**inputs)
>>> answer_start_index = outputs.start_logits.argmax()
>>> answer_end_index = outputs.end_logits.argmax()
>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
>>> # target is "nice puppet"
>>> target_start_index = torch.tensor([14])
>>> target_end_index = torch.tensor([15])
>>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
>>> loss = outputs.lossTFLEDModel
class transformers.TFLEDModel
< source >( config *inputs **kwargs )
Parameters
- config (LEDConfig) — 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 LED 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 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.
TensorFlow models and layers in transformers accept two formats as input:
- having all inputs as keyword arguments (like PyTorch models), or
- having all inputs as a list, tuple or dict in the first positional argument.
The reason the second format is supported is that Keras methods prefer this format when passing inputs to models
and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just
pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second
format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with
the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first
positional argument:
- a single Tensor with
input_idsonly 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})
Note that when creating models and layers with subclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!
call
< source >( input_ids: TFModelInputType | None = None attention_mask: tf.Tensor | None = None decoder_input_ids: tf.Tensor | None = None decoder_attention_mask: tf.Tensor | None = None head_mask: tf.Tensor | None = None decoder_head_mask: tf.Tensor | None = None encoder_outputs: tf.Tensor | None = None global_attention_mask: tf.Tensor | None = None past_key_values: Tuple[Tuple[tf.Tensor]] | None = None inputs_embeds: tf.Tensor | None = None decoder_inputs_embeds: tf.Tensor | None = None use_cache: bool | None = None output_attentions: bool | None = None output_hidden_states: bool | None = None return_dict: bool | None = None training: bool = False **kwargs ) → transformers.models.led.modeling_tf_led.TFLEDSeq2SeqModelOutput or tuple(tf.Tensor)
Parameters
- input_ids (
tf.Tensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
tf.Tensorof 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.Tensorof shape(batch_size, target_sequence_length), optional) — Indices of decoder input sequence tokens in the vocabulary.Indices can be obtained using
LedTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.LED uses the
eos_token_idas the starting token fordecoder_input_idsgeneration. Ifpast_key_valuesis used, optionally only the lastdecoder_input_idshave to be input (seepast_key_values). - decoder_attention_mask (
tf.Tensorof 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.Tensorof 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.Tensorof 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.
- encoder_outputs (
tf.Tensor, 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_valuesare 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_idsof shape(batch_size, sequence_length). - use_cache (
bool, optional, defaults toTrue) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). Set toFalseduring training,Trueduring generation - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder 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_statesunder 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
transformers.models.led.modeling_tf_led.TFLEDSeq2SeqModelOutput or tuple(tf.Tensor)
A transformers.models.led.modeling_tf_led.TFLEDSeq2SeqModelOutput 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 (LEDConfig) and inputs.
-
last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the decoder of the model.If
past_key_valuesis 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=Trueis passed or whenconfig.use_cache=True) — List oftf.Tensorof 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_valuesinput) to speed up sequential decoding. -
decoder_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
-
encoder_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. -
encoder_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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.
-
encoder_global_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
The TFLEDModel 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 AutoTokenizer, TFLEDModel
>>> import tensorflow as tf
>>> tokenizer = AutoTokenizer.from_pretrained("allenai/led-base-16384")
>>> model = TFLEDModel.from_pretrained("allenai/led-base-16384")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> outputs = model(inputs)
>>> last_hidden_states = outputs.last_hidden_stateTFLEDForConditionalGeneration
class transformers.TFLEDForConditionalGeneration
< source >( config *inputs **kwargs )
Parameters
- config (LEDConfig) — 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 LED 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 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.
TensorFlow models and layers in transformers accept two formats as input:
- having all inputs as keyword arguments (like PyTorch models), or
- having all inputs as a list, tuple or dict in the first positional argument.
The reason the second format is supported is that Keras methods prefer this format when passing inputs to models
and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just
pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second
format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with
the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first
positional argument:
- a single Tensor with
input_idsonly 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})
Note that when creating models and layers with subclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!
call
< source >( input_ids: TFModelInputType | None = None attention_mask: np.ndarray | tf.Tensor | None = None decoder_input_ids: np.ndarray | tf.Tensor | None = None decoder_attention_mask: np.ndarray | tf.Tensor | None = None head_mask: np.ndarray | tf.Tensor | None = None decoder_head_mask: np.ndarray | tf.Tensor | None = None encoder_outputs: TFLEDEncoderBaseModelOutput | None = None global_attention_mask: np.ndarray | tf.Tensor | None = None past_key_values: Tuple[Tuple[Union[np.ndarray, tf.Tensor]]] | None = None inputs_embeds: np.ndarray | tf.Tensor | None = None decoder_inputs_embeds: np.ndarray | tf.Tensor | None = None use_cache: bool | None = None output_attentions: bool | None = None output_hidden_states: bool | None = None return_dict: bool | None = None labels: tf.Tensor | None = None training: bool = False ) → transformers.models.led.modeling_tf_led.TFLEDSeq2SeqLMOutput or tuple(tf.Tensor)
Parameters
- input_ids (
tf.Tensorof shape({0})) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
tf.Tensorof 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.Tensorof shape(batch_size, target_sequence_length), optional) — Indices of decoder input sequence tokens in the vocabulary.Indices can be obtained using
LedTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.LED uses the
eos_token_idas the starting token fordecoder_input_idsgeneration. Ifpast_key_valuesis used, optionally only the lastdecoder_input_idshave to be input (seepast_key_values). - decoder_attention_mask (
tf.Tensorof 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.Tensorof 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.Tensorof 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.
- encoder_outputs (
tf.Tensor, 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_valuesare 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_idsof shape(batch_size, sequence_length). - use_cache (
bool, optional, defaults toTrue) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). Set toFalseduring training,Trueduring generation - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder 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_statesunder 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
transformers.models.led.modeling_tf_led.TFLEDSeq2SeqLMOutput or tuple(tf.Tensor)
A transformers.models.led.modeling_tf_led.TFLEDSeq2SeqLMOutput 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 (LEDConfig) and inputs.
-
loss (
tf.Tensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. -
logits (
tf.Tensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
past_key_values (
List[tf.Tensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftf.Tensorof 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_valuesinput) to speed up sequential decoding. -
decoder_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
-
encoder_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model. -
encoder_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — 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=Trueis passed or whenconfig.output_attentions=True) — 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.
-
encoder_global_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, x), wherexis the number of tokens with global attention mask.Global attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Those are the attention weights from every token with global attention to every token in the sequence.
The TFLEDForConditionalGeneration 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.
Examples:
>>> from transformers import AutoTokenizer, TFLEDForConditionalGeneration
>>> import tensorflow as tf
>>> mname = "allenai/led-base-16384"
>>> tokenizer = AutoTokenizer.from_pretrained(mname)
>>> TXT = "My friends are <mask> but they eat too many carbs."
>>> model = TFLEDForConditionalGeneration.from_pretrained(mname)
>>> batch = tokenizer([TXT], return_tensors="tf")
>>> logits = model(inputs=batch.input_ids).logits
>>> probs = tf.nn.softmax(logits[0])
>>> # probs[5] is associated with the mask token