Transformers documentation

Longformer

Transformers

You are viewing v4.29.1 version. A newer version v4.46.3 is available.

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Longformer

Overview

The Longformer model was presented 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.

Tips:

Since the Longformer is based on RoBERTa, it doesn’t have token_type_ids. You don’t need to indicate which token belongs to which segment. Just separate your segments with the separation token tokenizer.sep_token (or </s>).
A transformer model replacing the attention matrices by sparse matrices to go faster. Often, the local context (e.g., what are the two tokens left and right?) is enough to take action for a given token. Some preselected input tokens are still given global attention, but the attention matrix has way less parameters, resulting in a speed-up. See the local attention section for more information.

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

Longformer Self Attention

Longformer self attention employs self attention on both a “local” context and a “global” context. Most tokens only attend “locally” to each other meaning that each token attends to its $\frac{1}{2} w$ previous tokens and $\frac{1}{2} w$ succeeding tokens with $w$ being the window length as defined in config.attention_window. Note that config.attention_window can be of type List to define a different $w$ for each layer. A selected few tokens attend “globally” to all other tokens, as it is conventionally done for all tokens in BertSelfAttention.

Note that “locally” and “globally” attending tokens are projected by different query, key and value matrices. Also note that every “locally” attending token not only attends to tokens within its window $w$ , but also to all “globally” attending tokens so that global attention is symmetric.

The user can define which tokens attend “locally” and which tokens attend “globally” by setting the tensor global_attention_mask at run-time appropriately. All Longformer models employ the following logic for global_attention_mask:

0: the token attends “locally”,
1: the token attends “globally”.

For more information please also refer to forward() method.

Using Longformer self attention, the memory and time complexity of the query-key matmul operation, which usually represents the memory and time bottleneck, can be reduced from $\mathcal{O}(n_s \times n_s)$ to $\mathcal{O}(n_s \times w)$ , with $n_s$ being the sequence length and $w$ being the average window size. It is assumed that the number of “globally” attending tokens is insignificant as compared to the number of “locally” attending tokens.

For more information, please refer to the official paper.

Training

LongformerForMaskedLM is trained the exact same way RobertaForMaskedLM is trained and should be used as follows:

input_ids = tokenizer.encode("This is a sentence from [MASK] training data", return_tensors="pt")
mlm_labels = tokenizer.encode("This is a sentence from the training data", return_tensors="pt")

loss = model(input_ids, labels=input_ids, masked_lm_labels=mlm_labels)[0]

Transformers

Longformer

Overview

Longformer Self Attention

Training

Documentation resources

LongformerConfig

class transformers.LongformerConfig

LongformerTokenizer

class transformers.LongformerTokenizer

build_inputs_with_special_tokens

convert_tokens_to_string

create_token_type_ids_from_sequences

get_special_tokens_mask

LongformerTokenizerFast

class transformers.LongformerTokenizerFast

create_token_type_ids_from_sequences

Longformer specific outputs

class transformers.models.longformer.modeling_longformer.LongformerBaseModelOutput

class transformers.models.longformer.modeling_longformer.LongformerBaseModelOutputWithPooling

class transformers.models.longformer.modeling_longformer.LongformerMaskedLMOutput

class transformers.models.longformer.modeling_longformer.LongformerQuestionAnsweringModelOutput

class transformers.models.longformer.modeling_longformer.LongformerSequenceClassifierOutput

class transformers.models.longformer.modeling_longformer.LongformerMultipleChoiceModelOutput

class transformers.models.longformer.modeling_longformer.LongformerTokenClassifierOutput

class transformers.models.longformer.modeling_tf_longformer.TFLongformerBaseModelOutput

class transformers.models.longformer.modeling_tf_longformer.TFLongformerBaseModelOutputWithPooling

class transformers.models.longformer.modeling_tf_longformer.TFLongformerMaskedLMOutput

class transformers.models.longformer.modeling_tf_longformer.TFLongformerQuestionAnsweringModelOutput

class transformers.models.longformer.modeling_tf_longformer.TFLongformerSequenceClassifierOutput

class transformers.models.longformer.modeling_tf_longformer.TFLongformerMultipleChoiceModelOutput

class transformers.models.longformer.modeling_tf_longformer.TFLongformerTokenClassifierOutput

LongformerModel

class transformers.LongformerModel

forward

LongformerForMaskedLM

class transformers.LongformerForMaskedLM

forward

LongformerForSequenceClassification

class transformers.LongformerForSequenceClassification

forward

LongformerForMultipleChoice

class transformers.LongformerForMultipleChoice

forward

LongformerForTokenClassification

class transformers.LongformerForTokenClassification

forward

LongformerForQuestionAnswering

class transformers.LongformerForQuestionAnswering

forward

TFLongformerModel

class transformers.TFLongformerModel

call

TFLongformerForMaskedLM

class transformers.TFLongformerForMaskedLM

call

TFLongformerForQuestionAnswering

class transformers.TFLongformerForQuestionAnswering

call

TFLongformerForSequenceClassification

class transformers.TFLongformerForSequenceClassification

call

TFLongformerForTokenClassification

class transformers.TFLongformerForTokenClassification

call

TFLongformerForMultipleChoice

class transformers.TFLongformerForMultipleChoice

call