未验证 提交 894a0e69 编写于 作者: X Xiaoyao Xi 提交者: GitHub

Update README.md

上级 0d5612d7
...@@ -112,7 +112,7 @@ You can easily re-produce following competitive results with minor codes, which ...@@ -112,7 +112,7 @@ You can easily re-produce following competitive results with minor codes, which
## Package Overview ## Overview
<p align="center"> <p align="center">
<img src="https://github.com/PaddlePaddle/PALM/blob/master/img/architecture.png" alt="Sample" width="582" height="289"> <img src="https://github.com/PaddlePaddle/PALM/blob/master/img/architecture.png" alt="Sample" width="582" height="289">
...@@ -121,6 +121,10 @@ You can easily re-produce following competitive results with minor codes, which ...@@ -121,6 +121,10 @@ You can easily re-produce following competitive results with minor codes, which
</p> </p>
</p> </p>
PaddlePALM is a well-designed high-level NLP framework. You can efficiently achieve **supervised learning, unsupervised/self-supervised learning, multi-task learning and transfer learning** with minor codes based on PaddlePALM. There are three layers in PaddlePALM architecture, i.e., component layer, trainer layer and high-level trainer layer from bottom to top.
In component layer, PaddlePALM supplies 7 **decoupled** components to achieve a NLP task. Each component contains rich `pre-defined Classes` and a `Base Class`. Pre-defined classes are aiming at typical NLP tasks, and the base class is to help users develop a new Class (based on pre-defined ones or from the base).
| module | illustration | | module | illustration |
| - | - | | - | - |
| **paddlepalm** | an open source NLP pretraining and multitask learning framework, built on paddlepaddle. | | **paddlepalm** | an open source NLP pretraining and multitask learning framework, built on paddlepaddle. |
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册