Add LayoutLM Model (#7064)

* first version

* finish test docs readme model/config/tokenization class

* apply make style and make quality

* fix layoutlm GitHub link

* fix conflict in index.rst and add layoutlm to pretrained_models.rst

* fix bug in test_parents_and_children_in_mappings

* reformat modeling_auto.py and tokenization_auto.py

* fix bug in test_modeling_layoutlm.py

* Update docs/source/model_doc/layoutlm.rst

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update docs/source/model_doc/layoutlm.rst

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* remove inh, add tokenizer fast, and update some doc

* copy and rename necessary class from modeling_bert to modeling_layoutlm

* Update src/transformers/configuration_layoutlm.py

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Update src/transformers/configuration_layoutlm.py

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Update src/transformers/configuration_layoutlm.py

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Update src/transformers/configuration_layoutlm.py

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Update src/transformers/modeling_layoutlm.py

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Update src/transformers/modeling_layoutlm.py

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Update src/transformers/modeling_layoutlm.py

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* add mish to activations.py, import ACT2FN and import logging from utils

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
This commit is contained in:
Minghao Li
2020-09-22 21:28:02 +08:00
committed by GitHub
parent 244e1b5ba3
commit cd9a0585ea
14 changed files with 1510 additions and 3 deletions

View File

@@ -408,3 +408,11 @@ For a list that includes community-uploaded models, refer to `https://huggingfac
| | | |
| | | (see `details <https://github.com/laiguokun/Funnel-Transformer>`__) |
+--------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| LayoutLM | ``microsoft/layoutlm-base-uncased`` | | 12 layers, 768-hidden, 12-heads, 113M parameters |
| | | |
| | | (see `details <https://github.com/microsoft/unilm/tree/master/layoutlm>`__) |
+ +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| | ``microsoft/layoutlm-large-uncased`` | | 24 layers, 1024-hidden, 16-heads, 343M parameters |
| | | |
| | | (see `details <https://github.com/microsoft/unilm/tree/master/layoutlm>`__) |
+--------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+