README.md 3.99 KB
Newer Older
1
2
3
4
5
6
7
8
# Generative Pre-Training2(GPT2)

## 模型介绍
GPT2模型:第二代生成式预训练模型(Generative Pre-Training2)。

## 模型结构
GPT2主要使用Transformer的Decoder模块为特征提取器,并对Transformer Decoder进行了一些改动,原本的Decoder包含了两个Multi-Head Attention结构,而GPT2只保留了Mask Multi-Head Attention。

liucong's avatar
liucong committed
9
10
## Python版本推理

liucong's avatar
liucong committed
11
本次采用GPT-2模型进行诗词生成任务,模型文件下载链接:https://pan.baidu.com/s/1KWeoUuakCZ5dualK69qCcw , 提取码:4pmh ,并将GPT2_shici.onnx模型文件保存在Resource/文件夹下。下面介绍如何运行python代码示例,Python示例的详细说明见Doc目录下的Tutorial_Python.md。
liucong's avatar
liucong committed
12

liucong's avatar
liucong committed
13
### 下载镜像
14

liucong's avatar
liucong committed
15
在光源中下载MIGraphX镜像: 
16
17

```python
18
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
19
20
```

liucong's avatar
liucong committed
21
### 设置Python环境变量
liucong's avatar
liucong committed
22

liucong's avatar
liucong committed
23
24
25
```
export PYTHONPATH=/opt/dtk/lib:$PYTHONPATH
```
liucong's avatar
liucong committed
26

liucong's avatar
liucong committed
27
### 安装依赖
liucong's avatar
liucong committed
28
29

```python
liucong's avatar
liucong committed
30
31
# 进入gpt2 migraphx工程根目录
cd <path_to_gpt2_migraphx> 
liucong's avatar
liucong committed
32
33
34
35
36
37
38
39

# 进入示例程序目录
cd ./Python/

# 安装依赖
pip install -r requirements.txt
```

liucong's avatar
liucong committed
40
### 设置动态shape模式
41
42

```python
liucong's avatar
liucong committed
43
44
45
export MIGRAPHX_DYNAMIC_SHAPE=1
```

liucong's avatar
liucong committed
46
47
48
### 运行示例

在Python目录下执行如下命令运行该示例程序:
liucong's avatar
liucong committed
49
50
51

```python
python gpt2.py
52
53
```

liucong's avatar
liucong committed
54
55
如下所示,采用交互式界面,通过输入开头诗词,GPT2模型可以生成后续的诗句。

liucong's avatar
liucong committed
56
57
58
59
60
61
62
63
64
65
```
user:江上归帆天际开
chatbot:江上归帆天际开,江头别棹日边回。风尘满地音书绝,鸿雁不来春又来。
user:我亦孤山冷淡郎
chatbot:我亦孤山冷淡郎,爱梅不作一般香。水边篱落坡仙笑,羔酒空浇入甲黄。
user:七言绝句
chatbot:七言绝句古无有,五字长城今在前。我欲从君乞妙语,笔端三昧要亲传。
user:春风吹絮满江南
chatbot:春风吹絮满江南,一片离情酒半酣。记得小桥和雪看,梅花无数簇晴岚。
```
liucong's avatar
liucong committed
66
67
68

## C++版本推理

liucong's avatar
liucong committed
69
本次采用GPT-2模型进行诗词生成任务,模型文件下载链接:https://pan.baidu.com/s/1KWeoUuakCZ5dualK69qCcw , 提取码:4pmh ,并将GPT2_shici.onnx模型文件保存在Resource/文件夹下。下面介绍如何运行C++代码示例,C++示例的详细说明见Doc目录下的Tutorial_Cpp.md。
liucong's avatar
liucong committed
70

liucong's avatar
liucong committed
71
### 下载镜像
liucong's avatar
liucong committed
72

liucong's avatar
liucong committed
73
74
75
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
```
76

liucong's avatar
liucong committed
77
### 修改CMakeLists.txt
78

liucong's avatar
liucong committed
79
80
如果使用ubuntu系统,需要修改CMakeLists.txt中依赖库路径:
将"${CMAKE_CURRENT_SOURCE_DIR}/depend/lib64/"修改为"${CMAKE_CURRENT_SOURCE_DIR}/depend/lib/"
81
82


liucong's avatar
liucong committed
83
### 构建工程
84
85
86
87
88
89
90
91
92
93
94
95

```
rbuild build -d depend
```

### 设置环境变量

将依赖库依赖加入环境变量LD_LIBRARY_PATH,在~/.bashrc中添加如下语句:

**Centos**:

```
liucong's avatar
liucong committed
96
export LD_LIBRARY_PATH=<path_to_gpt2_migraphx>/depend/lib64/:$LD_LIBRARY_PATH
97
98
99
100
101
```

**Ubuntu**:

```
liucong's avatar
liucong committed
102
export LD_LIBRARY_PATH=<path_to_gpt2_migraphx>/depend/lib/:$LD_LIBRARY_PATH
103
104
105
106
107
108
```

然后执行:

```
source ~/.bashrc
109
110
```

liucong's avatar
liucong committed
111
### 设置动态shape模式
112

liucong's avatar
liucong committed
113
114
115
116
117
```
export MIGRAPHX_DYNAMIC_SHAPE=1
```

### 运行示例
118
119

```python
liucong's avatar
liucong committed
120
121
# 进入gpt2 migraphx工程根目录
cd <path_to_gpt2_migraphx> 
122

liucong's avatar
liucong committed
123
# 进入build目录
124
125
cd ./build/

liucong's avatar
liucong committed
126
127
# 执行示例程序
./GPT2
128
129
130
```

如下所示,采用交互式界面,通过输入开头诗词,GPT2模型可以推理出后续的诗句。
131

liucong's avatar
liucong committed
132
133
134
135
136
137
138
139
140
141
```
question:江上归帆天际开
chatbot:江上归帆天际开,江头别棹日边回。风尘满地音书绝,鸿雁不来春又来。
question:我亦孤山冷淡郎
chatbot:我亦孤山冷淡郎,爱梅不作一般香。水边篱落坡仙笑,羔酒空浇入甲黄。
question:七言绝句
chatbot:七言绝句古无有,五字长城今在前。我欲从君乞妙语,笔端三昧要亲传。
question:春风吹絮满江南
chatbot:春风吹絮满江南,一片离情酒半酣。记得小桥和雪看,梅花无数簇晴岚。
```
142

liucong's avatar
liucong committed
143
## 源码仓库及问题反馈
144
145
146

https://developer.hpccube.com/codes/modelzoo/gpt2_migraphx

liucong's avatar
liucong committed
147
## 参考
148
149

https://github.com/Morizeyao/GPT2-Chinese