------------------------------------
BART模型汇总
------------------------------------



下表汇总介绍了目前PaddleNLP支持的BART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                                                             |
+==================================================================================+==============+==================================================================================+
|``bart-base``                                                                     | English      | 12-layer, 768-hidden,                                                            |
|                                                                                  |              | 12-heads, 217M parameters.                                                       |
|                                                                                  |              | BART base model (English)                                                        |
+----------------------------------------------------------------------------------+--------------+----------------------------------------------------------------------------------+
|``bart-large``                                                                    | English      | 24-layer, 768-hidden,                                                            |
|                                                                                  |              | 16-heads, 509M parameters.                                                       |
|                                                                                  |              | BART large model (English)                                                       |
+----------------------------------------------------------------------------------+--------------+----------------------------------------------------------------------------------+