mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-06 22:30:09 +06:00
2422cda01b
* add new model prophetnet prophetnet modified modify codes as suggested v1 add prophetnet test files * still bugs, because of changed output formats of encoder and decoder * move prophetnet into the latest version * clean integration tests * clean tokenizers * add xlm config to init * correct typo in init * further refactoring * continue refactor * save parallel * add decoder_attention_mask * fix use_cache vs. past_key_values * fix common tests * change decoder output logits * fix xlm tests * make common tests pass * change model architecture * add tokenizer tests * finalize model structure * no weight mapping * correct n-gram stream attention mask as discussed with qweizhen * remove unused import * fix index.rst * fix tests * delete unnecessary code * add fast integration test * rename weights * final weight remapping * save intermediate * Descriptions for Prophetnet Config File * finish all models * finish new model outputs * delete unnecessary files * refactor encoder layer * add dummy docs * code quality * fix tests * add model pages to doctree * further refactor * more refactor, more tests * finish code refactor and tests * remove unnecessary files * further clean up * add docstring template * finish tokenizer doc * finish prophetnet * fix copies * fix typos * fix tf tests * fix fp16 * fix tf test 2nd try * fix code quality * add test for each model * merge new tests to branch * Update model_cards/microsoft/prophetnet-large-uncased-cnndm/README.md Co-authored-by: Sam Shleifer <sshleifer@gmail.com> * Update model_cards/microsoft/prophetnet-large-uncased-cnndm/README.md Co-authored-by: Sam Shleifer <sshleifer@gmail.com> * Update src/transformers/modeling_prophetnet.py Co-authored-by: Sam Shleifer <sshleifer@gmail.com> * Update utils/check_repo.py Co-authored-by: Sam Shleifer <sshleifer@gmail.com> * apply sams and sylvains comments * make style * remove unnecessary code * Update README.md Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update README.md Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/configuration_prophetnet.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * implement lysandres comments * correct docs * fix isort * fix tokenizers * fix copies Co-authored-by: weizhen <weizhen@mail.ustc.edu.cn> Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Sam Shleifer <sshleifer@gmail.com> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
64 lines
3.5 KiB
ReStructuredText
64 lines
3.5 KiB
ReStructuredText
XLM-ProphetNet
|
|
-----------------------------------------------------------------------------------------------------------------------
|
|
|
|
**DISCLAIMER:** If you see something strange, file a `Github Issue
|
|
<https://github.com/huggingface/transformers/issues/new?assignees=&labels=&template=bug-report.md&title>`__ and assign
|
|
@patrickvonplaten
|
|
|
|
|
|
Overview
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
The XLM-ProphetNet model was proposed in `ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training, <https://arxiv.org/abs/2001.04063>`__ by Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang, Ming Zhou on 13 Jan, 2020.
|
|
|
|
XLM-ProphetNet is an encoder-decoder model and can predict n-future tokens for "ngram" language modeling instead of just the next token. Its architecture is identical to ProhpetNet, but the model was trained on the multi-lingual "wiki100" Wikipedia dump.
|
|
|
|
The abstract from the paper is the following:
|
|
|
|
*In this paper, we present a new sequence-to-sequence pre-training model called ProphetNet, which introduces a novel self-supervised objective named future n-gram prediction and the proposed n-stream self-attention mechanism. Instead of the optimization of one-step ahead prediction in traditional sequence-to-sequence model, the ProphetNet is optimized by n-step ahead prediction which predicts the next n tokens simultaneously based on previous context tokens at each time step. The future n-gram prediction explicitly encourages the model to plan for the future tokens and prevent overfitting on strong local correlations. We pre-train ProphetNet using a base scale dataset (16GB) and a large scale dataset (160GB) respectively. Then we conduct experiments on CNN/DailyMail, Gigaword, and SQuAD 1.1 benchmarks for abstractive summarization and question generation tasks. Experimental results show that ProphetNet achieves new state-of-the-art results on all these datasets compared to the models using the same scale pre-training corpus.*
|
|
|
|
The Authors' code can be found `here <https://github.com/microsoft/ProphetNet>`__.
|
|
|
|
XLMProphetNetConfig
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: transformers.XLMProphetNetConfig
|
|
:members:
|
|
|
|
|
|
XLMProphetNetTokenizer
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: transformers.XLMProphetNetTokenizer
|
|
:members:
|
|
|
|
|
|
XLMProphetNetModel
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: transformers.XLMProphetNetModel
|
|
|
|
|
|
XLMProphetNetEncoder
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: transformers.XLMProphetNetEncoder
|
|
|
|
|
|
XLMProphetNetDecoder
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: transformers.XLMProphetNetDecoder
|
|
|
|
|
|
XLMProphetNetForConditionalGeneration
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: transformers.XLMProphetNetForConditionalGeneration
|
|
|
|
|
|
XLMProphetNetForCausalLM
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: transformers.XLMProphetNetForCausalLM
|