Skip to content

Commit 8c8fc03

Browse files
author
gongenlei
authored
Merge branch 'develop' into feat_beam_search_v2
2 parents b280a02 + 5c58459 commit 8c8fc03

File tree

100 files changed

+9957
-292
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

100 files changed

+9957
-292
lines changed

‎docs/community/contribute_models/importing_awesome_pretrained_models.rst‎ renamed to ‎docs/community/contribute_models/contribute_awesome_pretrained_models.rst‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
==========================================
2-
贡献优质的预训练模型权重
2+
贡献优质的模型权重
33
==========================================
44

55
1. 模型网络结构种类

‎docs/community/contribute_models/contribute_new_models.rst‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
==========================================
2+
贡献新模型
3+
==========================================

‎docs/community/contribute_models/convert_pytorch_to_paddle.rst‎

Lines changed: 109 additions & 114 deletions
Large diffs are not rendered by default.

‎docs/community/contribute_models/index.rst‎

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
1+
============
2+
如何贡献模型
3+
============
4+
5+
.. toctree::
6+
:maxdepth: 1
7+
8+
convert_pytorch_to_paddle.rst
9+
contribute_awesome_pretrained_models.rst
10+
contribute_new_models.rst

‎docs/get_started/quick_start.rst‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@
1919

2020
情感分析本质是一个文本分类任务。PaddleNLP内置了ERNIE、BERT、RoBERTa、Electra等丰富的预训练模型，并且内置了各种预训练模型对于不同下游任务的Fine-tune网络。用户可以使用PaddleNLP提供的模型，完成问答、序列分类、token分类等任务。查阅 预训练模型_ 了解更多。这里以ERNIE模型为例，介绍如何将预训练模型Fine-tune完成文本分类任务。
2121

22-
.. _预训练模型: https://paddlenlp.readthedocs.io/en/latest/modelzoo/transformer.html
22+
.. _预训练模型: https://paddlenlp.readthedocs.io/zh/latest/model_zoo/transformers.html
2323

2424
加载预训练模型ERNIE
2525

‎docs/index.rst‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -71,8 +71,8 @@
7171
:maxdepth: 2
7272
:caption: 社区交流共建
7373

74+
如何贡献模型 <community/contribute_models/index>
7475
如何贡献数据集 <community/contribute_datasets/index>
75-
如何贡献模型 <community/contribute_models>
7676
如何贡献文档案例 <community/contribute_docs>
7777
如何加入兴趣小组 <community/join_in_PaddleNLP-SIG>
7878

‎docs/model_zoo/transformers.rst‎

Lines changed: 13 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -9,8 +9,8 @@ PaddleNLP为用户提供了常用的 ``BERT``、``ERNIE``、``ALBERT``、``RoBER
99
Transformer预训练模型汇总
1010
------------------------------------
1111

12-
下表汇总了介绍了目前PaddleNLP支持的各类预训练模型以及对应预训练权重。我们目前提供了 **68** 种预训练的参数权重供用户使用，
13-
其中包含了 **33** 种中文语言模型的预训练权重。
12+
下表汇总了介绍了目前PaddleNLP支持的各类预训练模型以及对应预训练权重。我们目前提供了 **70** 种预训练的参数权重供用户使用，
13+
其中包含了 **34** 种中文语言模型的预训练权重。
1414

1515
+--------------------+-------------------------------------+--------------+-----------------------------------------+
1616
| Model | Pretrained Weight | Language | Details of the model |
@@ -171,6 +171,14 @@ Transformer预训练模型汇总
171171
| | | | 16-heads, 336M parameters. |
172172
| | | | Trained on lower-cased English text. |
173173
+--------------------+-------------------------------------+--------------+-----------------------------------------+
174+
|ERNIE-DOC_ |``ernie-doc-base-zh`` | Chinese | 12-layer, 768-hidden, |
175+
| | | | 12-heads, 108M parameters. |
176+
| | | | Trained on Chinese text. |
177+
| +-------------------------------------+--------------+-----------------------------------------+
178+
| |``ernie-doc-base-en`` | English | 12-layer, 768-hidden, |
179+
| | | | 12-heads, 103M parameters. |
180+
| | | | Trained on lower-cased English text. |
181+
+--------------------+-------------------------------------+--------------+-----------------------------------------+
174182
|ERNIE-GEN_ |``ernie-gen-base-en`` | English | 12-layer, 768-hidden, |
175183
| | | | 12-heads, 108M parameters. |
176184
| | | | Trained on lower-cased English text. |
@@ -332,6 +340,8 @@ Transformer预训练模型适用任务汇总
332340
+--------------------+-------------------------+----------------------+--------------------+-----------------+
333341
|ERNIE_ | ✅ | ✅ | ✅ | ❌ |
334342
+--------------------+-------------------------+----------------------+--------------------+-----------------+
343+
|ERNIE-DOC_ | ✅ | ✅ | ✅ | ❌ |
344+
+--------------------+-------------------------+----------------------+--------------------+-----------------+
335345
|ERNIE-GEN_ | ❌ | ❌ | ❌ | ✅ |
336346
+--------------------+-------------------------+----------------------+--------------------+-----------------+
337347
|ERNIE-GRAM_ | ✅ | ✅ | ✅ | ❌ |
@@ -357,6 +367,7 @@ Transformer预训练模型适用任务汇总
357367
.. _DistilBert: https://arxiv.org/abs/1910.01108
358368
.. _ELECTRA: https://arxiv.org/abs/2003.10555
359369
.. _ERNIE: https://arxiv.org/abs/1904.09223
370+
.. _ERNIE-DOC: https://arxiv.org/abs/2012.15688
360371
.. _ERNIE-GEN: https://arxiv.org/abs/2001.11314
361372
.. _ERNIE-GRAM: https://arxiv.org/abs/2010.12148
362373
.. _GPT: https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf

‎docs/source/paddlenlp.ops.optimizer.adamwdl.rst‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
adamwdl
2+
====================================
3+
4+
.. automodule:: paddlenlp.ops.optimizer.adamwdl
5+
:members:
6+
:no-undoc-members:
7+
:show-inheritance:

‎docs/source/paddlenlp.ops.optimizer.rst‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -12,3 +12,4 @@ optimizer
1212

1313
paddlenlp.ops.optimizer.AdamwOptimizer
1414
paddlenlp.ops.optimizer.adamw
15+
paddlenlp.ops.optimizer.adamwdl

‎docs/source/paddlenlp.transformers.ernie_doc.modeling.rst‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
modeling
2+
==============================================
3+
4+
.. automodule:: paddlenlp.transformers.ernie_doc.modeling
5+
:members:
6+
:no-undoc-members:
7+
:show-inheritance:

0 commit comments

Comments
 (0)