未验证 提交 59568bbb 编写于 作者: D DanielYang 提交者: GitHub

test=update_yaml_onlinedemo, test=release/2.3 (#5676)

上级 a0264403
......@@ -14,4 +14,4 @@ Datasets: "deepcfd-data"
Publisher: "Baidu"
License: "apache.2.0"
IfTraining: 1
IfOnlineDemo: 1
IfOnlineDemo: 0
......@@ -14,4 +14,4 @@ Datasets: ""
Publisher: "Baidu"
License: "apache.2.0"
IfTraining: 0
IfOnlineDemo: 1
IfOnlineDemo: 0
......@@ -8,7 +8,7 @@
"source": [
"## 1. ERNIE 3.0 Zeus 模型简介\n",
"\n",
"ERNIE 3.0 Zeus 是 ERNIE 3.0 系列模型的最新升级。其除了对无标注数据和知识图谱的学习之外,还通过持续学习对百余种不同形式的任务数据学习。实现了任务知识增强,显著提升了模型的零样本/小样本学习能力。\n",
"ERNIE 3.0 Zeus 是 ERNIE 3.0 系列模型的最新升级。其除了对无标注数据和知识图谱的学习之外,还通过持续学习对百余种不同形式的任务数据学习。实现了任务知识增强,显著提升了模型的零样本/小样本学习能力。[点击此处进入体验页面](https://wenxin.baidu.com/ernie3)\n",
"\n",
"## 2. 模型原理介绍\n",
"\n",
......@@ -20,7 +20,7 @@
" \n",
"#### 温馨提示\n",
"\n",
"每个账户每日免费请求ERNIE 3.0系列服务的上限为200条输入,免费请求额度共2000条输入。如果您有更多请求需求,请跟我们联系:[体验申请](https://wenxin.baidu.com/wenxin/apply3)\n",
"* 每个账户每日免费请求ERNIE 3.0系列服务的上限为200条输入,免费请求额度共2000条输入。如果您有更多请求额度需求和商务合作需求,请跟我们联系:[体验申请](https://wenxin.baidu.com/wenxin/apply3)\n",
"\n",
"\n",
"#### 获取API Key\n",
......@@ -34,11 +34,32 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple\n",
"Collecting wenxin-api\n",
" Downloading https://pypi.tuna.tsinghua.edu.cn/packages/0e/32/fb1e931cc0436205fb53193a4c1f9fd8aae75ba71dbd999fd55b9899428b/wenxin_api-0.1.0-py3-none-any.whl (24 kB)\n",
"Requirement already satisfied: tqdm in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from wenxin-api) (4.64.1)\n",
"Requirement already satisfied: requests>=2.20 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from wenxin-api) (2.24.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests>=2.20->wenxin-api) (2019.9.11)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests>=2.20->wenxin-api) (3.0.4)\n",
"Requirement already satisfied: idna<3,>=2.5 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests>=2.20->wenxin-api) (2.8)\n",
"Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests>=2.20->wenxin-api) (1.25.6)\n",
"Installing collected packages: wenxin-api\n",
"Successfully installed wenxin-api-0.1.0\n",
"\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.1.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m22.3.1\u001b[0m\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
]
}
],
"source": [
"!pip install --upgrade wenxin-api"
]
......@@ -107,7 +128,7 @@
"\n",
"## 5. 应用场景\n",
"\n",
"智能创作、摘要生成、问答、语义检索、情感分析、信息抽取、文本匹配、文本纠错等各类自然语言理解和生成任务\n",
"智能创作、摘要生成、问答、语义检索、情感分析、信息抽取、文本匹配、文本纠错等各类自然语言理解和生成任务\n",
"\n",
"## 6. 使用方案\n",
"\n",
......@@ -115,11 +136,11 @@
"\n",
"#### 通过飞桨旸谷社区在线体验\n",
"\n",
"通过飞桨旸谷社区在线体验 ERNIE 3.0 Zeus 的文本理解和文本创作能力,您可以通过 ERNIE 3.0 Zeus Prompt 接口体验预置 prompt 技能,预置技能包括作文创作、文案创作、摘要生成、问题生成、古诗创作、对联续写、小说续写、自由问答、情感分析、信息抽取、同义改写、文本匹配、文本纠错、完型填空、Text2SQL 等十余种预置技能,也可以自定义 prompt 体验 ERNIE 3.0 Zeus 强大的零样本、小样本自然语言处理能力。同样的,通过 ERNIE3.0 Zeus 接口您可以随意输入内容,体验模型强大的续写能力。\n",
"通过飞桨旸谷社区[在线体验](https://wenxin.baidu.com/ernie3) ERNIE 3.0 Zeus 的文本理解和文本创作能力,您可以通过 ERNIE 3.0 Zeus Prompt 接口体验预置 prompt 技能,预置技能包括作文创作、文案创作、摘要生成、问题生成、古诗创作、对联续写、小说续写、自由问答、情感分析、信息抽取、同义改写、文本匹配、文本纠错、完型填空、Text2SQL 等十余种预置技能,也可以自定义 prompt 体验 ERNIE 3.0 Zeus 强大的零样本、小样本自然语言处理能力。同样的,通过 ERNIE3.0 Zeus 接口您可以随意输入内容,体验模型强大的续写能力。\n",
"\n",
"#### 通过 API 调用体验\n",
"\n",
"ERNIE 3.0 Zeus 提供[ API 体验调用的入口](https://wenxin.baidu.com/ernie3),您也可以在飞桨旸谷社区 API 体验专区申请 AK、SK 进行接口调用体验。\n"
"ERNIE 3.0 Zeus 提供API体验调用的入口,您也可以在飞桨旸谷社区 API 体验专区申请 AK、SK 进行接口调用体验(上述已给出API接口调用体验流程)。"
]
}
],
......
......@@ -33,5 +33,5 @@ License: "apache.2.0"
Paper:
- title: "ERNIE-Tiny: A Progressive Distillation Framework for Pretrained Transformer Compression"
url: "https://arxiv.org/abs/2106.02241"
IfTraining: 0
IfOnlineDemo: 1
\ No newline at end of file
IfTraining: 1
IfOnlineDemo: 0
\ No newline at end of file
......@@ -31,4 +31,4 @@ Paper:
- title: "ERNIE-Layout: Layout-Knowledge Enhanced Multi-modal Pre-training for Document Understanding"
url: https://arxiv.org/pdf/2210.06155.pdf
IfTraining: 1
IfOnlineDemo: 1
\ No newline at end of file
IfOnlineDemo: 0
\ No newline at end of file
......@@ -22,5 +22,5 @@ Paper:
- title: "ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual\
\ Semantics with Monolingual Corpora"
url: "https://arxiv.org/pdf/2012.15674.pdf"
IfTraining: 0
IfTraining: 1
IfOnlineDemo: 0
\ No newline at end of file
......@@ -65,5 +65,5 @@ License: "apache.2.0"
Paper:
- title: "Unified Structure Generation for Universal Information Extraction"
url: "https://arxiv.org/pdf/2203.12277.pdf"
IfTraining: 0
IfTraining: 1
IfOnlineDemo: 1
\ No newline at end of file
......@@ -14,4 +14,4 @@ Datasets: ""
Publisher: "Baidu"
License: "apache.2.0"
IfTraining: 0
IfOnlineDemo: 1
IfOnlineDemo: 0
......@@ -8,7 +8,7 @@
"source": [
"## 1. ERNIE-ViLG模型简介\n",
"\n",
"ERNIE-ViLG是一个知识增强跨模态图文生成大模型,将文生成图和图生成文任务融合到同一个模型进行端到端的学习,从而实现文本和图像的跨模态语义对齐。可以支持用户进行内容创作,让每个用户都能够体验到一个低门槛的创作平台。[点击此处进体验页面](https://wenxin.baidu.com/moduleApi/ernieVilg)\n",
"ERNIE-ViLG是一个知识增强跨模态图文生成大模型,将文生成图和图生成文任务融合到同一个模型进行端到端的学习,从而实现文本和图像的跨模态语义对齐。可以支持用户进行内容创作,让每个用户都能够体验到一个低门槛的创作平台。[点击此处进体验页面](https://wenxin.baidu.com/moduleApi/ernieVilg)\n",
"\n",
"## 2. 模型原理介绍\n",
"百度文心ERNIE-ViLG 模型提出统一的跨模态双向生成模型,通过自回归生成模式对图像生成和文本生成任务进行统一建模,更好地捕捉模态间的语义对齐关系,从而同时提升图文双向生成任务的效果。文心 ERNIE-ViLG 在文本生成图像的权威公开数据集 MS-COCO 上,图片质量评估指标 FID(Fréchet Inception Distance)远超 OpenAI 的DALL-E等同类模型,并刷新了图像描述多项任务的最好效果。此外,文心ERNIE-ViLG还凭借强大的跨模态理解能力,在生成式视觉问答任务上也取得了领先成绩。\n",
......@@ -20,7 +20,7 @@
"\n",
"* 温馨提示:\n",
"\n",
"每个账户每日免费请求ERNIE-ViLG API服务的上限为100条输入,免费请求额度共500条输入。如需提额,请在[合作咨询](https://wenxin.baidu.com/wenxin/apply)的需求描述里填写您的购买需求。\n",
"每个账户每日免费请求ERNIE-ViLG API服务的上限为100条输入,免费请求额度共500条输入。如需提额或者商务合作请在[合作咨询](https://wenxin.baidu.com/wenxin/apply)的需求描述里填写您的购买需求或者合作需求。\n",
"\n",
"### 获取API Key\n",
"\n",
......@@ -131,14 +131,13 @@
"\n",
"## 5. 使用方案\n",
"\n",
"\n",
"#### 通过飞桨旸谷社区在线体验\n",
"\n",
"通过飞桨旸谷社区在线体验 ERNIE-ViLG的文生图能力。\n",
"通过飞桨旸谷社区[在线体验](https://wenxin.baidu.com/moduleApi/ernieVilg) ERNIE-ViLG的文生图能力。\n",
"\n",
"#### 通过 API 调用体验\n",
"\n",
"ERNIE-ViLG 提供API体验调用的入口,您也可以在飞桨旸谷社区 API 体验专区申请 AK、SK 进行接口调用体验。"
"ERNIE-ViLG 提供API体验调用的入口,您也可以在飞桨旸谷社区 API 体验专区申请 AK、SK 进行接口调用体验(上述已给出API接口调用体验流程)。"
]
}
],
......
......@@ -22,4 +22,4 @@ Datasets: "cylinder2D_continuous"
Publisher: "Baidu"
License: "apache.2.0"
IfTraining: 1
IfOnlineDemo: 1
IfOnlineDemo: 0
......@@ -40,5 +40,5 @@ Example:
Datasets: ""
Publisher: "Baidu"
License: "apache.2.0"
IfTraining: 0
IfTraining: 1
IfOnlineDemo: 1
......@@ -26,4 +26,4 @@ Paper:
- title: "PP-MSVSR: Multi-Stage Video Super-Resolution"
url: "https://arxiv.org/pdf/2112.02828.pdf"
IfTraining: 1
IfOnlineDemo: 1
IfOnlineDemo: 0
......@@ -21,5 +21,5 @@ License: "apache.2.0"
Paper:
- title: "PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System"
url: "https://arxiv.org/abs/2109.03144"
IfTraining: 0
IfTraining: 1
IfOnlineDemo: 1
......@@ -42,5 +42,5 @@ License: "apache.2.0"
Paper:
- title: "PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System"
url: "https://arxiv.org/abs/2206.03001"
IfTraining: 0
IfTraining: 1
IfOnlineDemo: 1
......@@ -22,4 +22,4 @@ Publisher: "Baidu"
License: "apache.2.0"
Paper: ""
IfTraining: 1
IfOnlineDemo: 1
IfOnlineDemo: 0
......@@ -45,5 +45,5 @@ License: "apache.2.0"
Paper:
- title: "PP-StructureV2: A Stronger Document Analysis System"
url: "https://arxiv.org/abs/2210.05391v2"
IfTraining: 0
IfTraining: 1
IfOnlineDemo: 1
......@@ -24,5 +24,5 @@ Example:
Datasets: "COCO train2017,AI Challenger trainset,COCO person keypoints val2017,COCO instances val2017"
Publisher: "Baidu"
License: "apache.2.0"
IfTraining: 0
IfTraining: 1
IfOnlineDemo: 1
......@@ -24,5 +24,5 @@ Example:
Datasets: "BDD-100k"
Publisher: "Baidu"
License: "apache.2.0"
IfTraining: 0
IfTraining: 1
IfOnlineDemo: 1
# 模型列表
| 模型名称 | 模型简介 | 数据集 | 下载地址 |
|---|---|---|---|
| VSQL | 图片分类 | MNIST(0,1) | [预训练模型](https://release-data.cdn.bcebos.com/PaddleQuantum/vsql.pdparams) |
# Model list
| Model | Introduction | Dataset | Download |
|---|---|---|---|
| VSQL | Image classification | MNIST(0, 1) | [pretrained model](https://release-data.cdn.bcebos.com/PaddleQuantum/vsql.pdparams) |
---
Model_Info:
name: "PQ-VSQL"
description: "基于影子特征的量子-经典混合模型"
description_en: "Hybrid quantum-classical model based on the shadow features"
update_time:
icon: "https://user-images.githubusercontent.com/23690325/203944010-3f7e9373-d6d3-4bf5-989a-d5817b15e20f.png"
Task:
- tag: "量子计算"
tag_en: "Quantum Computing"
sub_tag: "变分影子量子学习"
sub_tag_en: "VSQL"
Datasets: MNIST
Pulisher: Baidu
License: Apache 2.0
Paper:
- title: "VSQL: Variational Shadow Quantum Learning for Classification"
url: https://ojs.aaai.org/index.php/AAAI/article/view/17016
IfTraining: 0
IfOnlineDemo: 0
\ No newline at end of file
此差异已折叠。
此差异已折叠。
......@@ -17,4 +17,4 @@ Paper:
- title: "Context Autoencoder for Self-Supervised Representation Learning"
url: "https://arxiv.org/abs/2202.03026"
IfTraining: 0
IfOnlineDemo: 1
\ No newline at end of file
IfOnlineDemo: 0
\ No newline at end of file
......@@ -17,4 +17,4 @@ Paper:
- title: "Structured Text Understanding with Multi-Modal Transformers"
url: "https://arxiv.org/pdf/2108.02923.pdf"
IfTraining: 0
IfOnlineDemo: 1
\ No newline at end of file
IfOnlineDemo: 0
\ No newline at end of file
......@@ -17,4 +17,4 @@ Paper:
- title: "UFO:Unified Feature Optimization"
url: "https://arxiv.org/pdf/2207.10341v1.pdf"
IfTraining: 0
IfOnlineDemo: 1
IfOnlineDemo: 0
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