Commit b5a7f01c authored by chenxj's avatar chenxj
Browse files

update README

parent 1d300d4e
......@@ -16,12 +16,13 @@ bert_large_squad模型的主要参数为:24个transformer层、1024个hidden s
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
docker run -d -t --privileged --device=/dev/kfd --device=/dev/dri/ --network=host --group-add video --name bert-test image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
docker exec -it bert-test bash
```
[huggingface](https://huggingface.co/ctuning/mlperf-inference-bert-onnx-fp32-squad-v1.1)下载模型model.onnx到当前目录
执行fp16转换
```
pip3 install onnxmltools
pip3 install -r requirements.txt
python3 fp16-convert.py
```
## 推理
......@@ -30,7 +31,7 @@ python3 main.py
```
## result
![image](https://developer.hpccube.com/codes/modelzoo/bert_large_squad_onnx/-/raw/main/resources/bert_result.png)
### 性能和精度数据
### 精度
暂无
## 应用场景
### 算法类别
......@@ -39,6 +40,6 @@ nlp
问答系统
## 源码仓库及问题反馈
https://developer.hpccube.com/codes/modelzoo/bert_large_squad_onnx
## 参考
## 参考资料
https://github.com/google-research/bert
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