Commit e37eee5a authored by liucong's avatar liucong
Browse files

修改readme

parent 501e81d6
......@@ -18,7 +18,7 @@ BERT的全称为Bidirectional Encoder Representation from Transformers,是一
## 环境配置
### Docker
### Docker(方法一)
拉取镜像:
......@@ -35,6 +35,15 @@ docker run --shm-size 16g --network=host --name=bert_migraphx --privileged --dev
source /opt/dtk/env.sh
```
### Dockerfile(方法二)
```
cd ./docker
docker build --no-cache -t bert_migraphx:2.0 .
docker run --shm-size 16g --network=host --name=bert_migraphx --privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v $PWD/bert_migraphx:/home/bert_migraphx -it <Your Image ID> /bin/bash
```
## 数据集
在界面中根据提示输入问题,模型预测出答案。
......@@ -134,6 +143,10 @@ question:What is ROCm built for?
answer:scale
```
### 精度
## 应用场景
### 算法类别
......@@ -148,6 +161,6 @@ answer:scale
https://developer.hpccube.com/codes/modelzoo/bert_migraphx
## 参考
## 参考资料
https://github.com/ROCmSoftwarePlatform/AMDMIGraphX/tree/develop/examples/nlp/python_bert_squad
\ No newline at end of file
FROM image.sourcefind.cn:5000/dcu/admin/base/migraphx:4.0.0-centos7.6-dtk23.04.1-py38-latest
RUN source /opt/dtk/env.sh
......@@ -5,6 +5,6 @@ modelName=bert_migraphx
# 模型描述
modelDescription=Bert是一种预训练的语言表征模型。
# 应用场景
appScenario=推理,NLP,对话问答
appScenario=推理,NLP,政府,科研,金融,教育
# 框架类型
frameType=migraphx
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment