Commit dac33d3a authored by dcuai's avatar dcuai
Browse files

Update dtk2404

parent 6d6a90c4
# bert_large_squad_onnxruntime
# bert_large_squad_
## 论文
[BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/pdf/1810.04805.pdf)
## 模型结构
......@@ -11,11 +11,12 @@ bert_large_squad模型的主要参数为:24个transformer层、1024个hidden s
![image](https://developer.hpccube.com/codes/modelzoo/bert_large_squad_onnx/-/raw/main/resources/squad.png)
## 数据集
暂无合适中文数据集
## 环境配置
[光源](https://www.sourcefind.cn/#/service-details)可拉取推理的docker镜像,在[光合开发者社区](https://cancon.hpccube.com:65024/4/main/)可下载onnxruntime安装包。bert_large_squad_onnx推荐的镜像如下:
[光源](https://www.sourcefind.cn/#/service-details)可拉取推理的docker镜像。bert_large_squad_onnx推荐的镜像如下:
```
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 pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.15.0_migraphx4.2.2_dtk2404
docker run -d -t --privileged --shm-size=32g --device=/dev/kfd --device=/dev/dri/ --network=host --group-add video --name bert-test -v /opt/hyhal:/opt/hyhal:ro image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.15.0_migraphx4.2.2_dtk2404 bash
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
......@@ -32,6 +33,7 @@ python3 fp16-convert.py
```
python3 main.py
```
## result
![image](https://developer.hpccube.com/codes/modelzoo/bert_large_squad_onnx/-/raw/main/resources/bert_result.png)
### 精度
......
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