------------------------------------
LayoutLMV2模型汇总
------------------------------------



下表汇总介绍了目前PaddleNLP支持的LayoutLMV2模型对应预训练权重。
关于模型的具体细节可以参考对应链接。

+----------------------------------------------------------------------------------+--------------+----------------------------------------------------------------------------------+
| Pretrained Weight                                                                | Language     | Details of the model                                                             |
+==================================================================================+==============+==================================================================================+
|``layoutlmv2-base-uncased``                                                       | English      | 12-layer, 768-hidden,                                                            |
|                                                                                  |              | 12-heads, 200M parameters.                                                       |
|                                                                                  |              | LayoutLmv2 base uncased model.                                                   |
+----------------------------------------------------------------------------------+--------------+----------------------------------------------------------------------------------+
|``layoutlmv2-large-uncased``                                                      | English      | 24-layer, 1024-hidden,                                                           |
|                                                                                  |              | 16-heads, _M parameters.                                                         |
|                                                                                  |              | LayoutLmv2 large uncased model.                                                  |
+----------------------------------------------------------------------------------+--------------+----------------------------------------------------------------------------------+