transformers/docs/source/model_doc/funnel.rst
2020-10-26 15:48:36 -04:00

185 lines
7.4 KiB
ReStructuredText

Funnel Transformer
-----------------------------------------------------------------------------------------------------------------------
Overview
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The Funnel Transformer model was proposed in the paper `Funnel-Transformer: Filtering out Sequential Redundancy for
Efficient Language Processing <https://arxiv.org/abs/2006.03236>`__. It is a bidirectional transformer model, like
BERT, but with a pooling operation after each block of layers, a bit like in traditional convolutional neural networks
(CNN) in computer vision.
The abstract from the paper is the following:
*With the success of language pretraining, it is highly desirable to develop more efficient architectures of good
scalability that can exploit the abundant unlabeled data at a lower cost. To improve the efficiency, we examine the
much-overlooked redundancy in maintaining a full-length token-level presentation, especially for tasks that only
require a single-vector presentation of the sequence. With this intuition, we propose Funnel-Transformer which
gradually compresses the sequence of hidden states to a shorter one and hence reduces the computation cost. More
importantly, by re-investing the saved FLOPs from length reduction in constructing a deeper or wider model, we further
improve the model capacity. In addition, to perform token-level predictions as required by common pretraining
objectives, Funnel-Transformer is able to recover a deep representation for each token from the reduced hidden sequence
via a decoder. Empirically, with comparable or fewer FLOPs, Funnel-Transformer outperforms the standard Transformer on
a wide variety of sequence-level prediction tasks, including text classification, language understanding, and reading
comprehension.*
Tips:
- Since Funnel Transformer uses pooling, the sequence length of the hidden states changes after each block of layers.
The base model therefore has a final sequence length that is a quarter of the original one. This model can be used
directly for tasks that just require a sentence summary (like sequence classification or multiple choice). For other
tasks, the full model is used; this full model has a decoder that upsamples the final hidden states to the same
sequence length as the input.
- The Funnel Transformer checkpoints are all available with a full version and a base version. The first ones should be
used for :class:`~transformers.FunnelModel`, :class:`~transformers.FunnelForPreTraining`,
:class:`~transformers.FunnelForMaskedLM`, :class:`~transformers.FunnelForTokenClassification` and
class:`~transformers.FunnelForQuestionAnswering`. The second ones should be used for
:class:`~transformers.FunnelBaseModel`, :class:`~transformers.FunnelForSequenceClassification` and
:class:`~transformers.FunnelForMultipleChoice`.
The original code can be found `here <https://github.com/laiguokun/Funnel-Transformer>`__.
FunnelConfig
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelConfig
:members:
FunnelTokenizer
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelTokenizer
:members: build_inputs_with_special_tokens, get_special_tokens_mask,
create_token_type_ids_from_sequences, save_vocabulary
FunnelTokenizerFast
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelTokenizerFast
:members:
Funnel specific outputs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.modeling_funnel.FunnelForPreTrainingOutput
:members:
.. autoclass:: transformers.modeling_tf_funnel.TFFunnelForPreTrainingOutput
:members:
FunnelBaseModel
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelBaseModel
:members: forward
FunnelModel
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelModel
:members: forward
FunnelModelForPreTraining
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelForPreTraining
:members: forward
FunnelForMaskedLM
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelForMaskedLM
:members: forward
FunnelForSequenceClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelForSequenceClassification
:members: forward
FunnelForMultipleChoice
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelForMultipleChoice
:members: forward
FunnelForTokenClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelForTokenClassification
:members: forward
FunnelForQuestionAnswering
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.FunnelForQuestionAnswering
:members: forward
TFFunnelBaseModel
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFFunnelBaseModel
:members: call
TFFunnelModel
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFFunnelModel
:members: call
TFFunnelModelForPreTraining
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFFunnelForPreTraining
:members: call
TFFunnelForMaskedLM
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFFunnelForMaskedLM
:members: call
TFFunnelForSequenceClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFFunnelForSequenceClassification
:members: call
TFFunnelForMultipleChoice
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFFunnelForMultipleChoice
:members: call
TFFunnelForTokenClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFFunnelForTokenClassification
:members: call
TFFunnelForQuestionAnswering
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFFunnelForQuestionAnswering
:members: call