------------------------------------
ERNIE-DOC模型汇总
------------------------------------



下表汇总介绍了目前PaddleNLP支持的ERNIE-DOC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                                                             |
+==================================================================================+==============+==================================================================================+
|``ernie-doc-base-zh``                                                             | Chinese      | 12-layer, 768-hidden,                                                            |
|                                                                                  |              | 12-heads, 108M parameters.                                                       |
|                                                                                  |              | Trained on Chinese text.                                                         |
+----------------------------------------------------------------------------------+--------------+----------------------------------------------------------------------------------+
|``ernie-doc-base-en``                                                             | English      | 12-layer, 768-hidden,                                                            |
|                                                                                  |              | 12-heads, 103M parameters.                                                       |
|                                                                                  |              | Trained on lower-cased English text.                                             |
+----------------------------------------------------------------------------------+--------------+----------------------------------------------------------------------------------+