Commit 460e2662 authored by zhuwenwen's avatar zhuwenwen
Browse files

update fa

parent fa44cada
FROM image.sourcefind.cn:5000/dcu/admin/base/custom:vllm0.3.3-dtk24.04-centos7.6-py310-v1
FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
ENV LANG C.UTF-8
RUN pip install aiohttp==3.9.1 outlines==0.0.37 openai==1.23.3 -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
\ No newline at end of file
......@@ -2,7 +2,7 @@
* @Author: zhuww
* @email: zhuww@sugon.com
* @Date: 2024-06-13 14:38:07
* @LastEditTime: 2024-06-13 16:16:01
* @LastEditTime: 2024-06-20 08:35:01
-->
## 论文
......@@ -42,12 +42,15 @@ ChatGLM系列模型基于GLM架构开发。GLM是一种基于Transformer的语
提供[光源](https://www.sourcefind.cn/#/image/dcu/custom)拉取推理的docker镜像:
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:vllm0.3.3-dtk24.04-centos7.6-py310-v1
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
# <Image ID>用上面拉取docker镜像的ID替换
# <Host Path>主机端路径
# <Container Path>容器映射路径
docker run -it --name chatglm_vllm --privileged --shm-size=64G --device=/dev/kfd --device=/dev/dri/ --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --ulimit memlock=-1:-1 --ipc=host --network host --group-add video -v /opt/hyhal:/opt/hyhal -v <Host Path>:<Container Path> <Image ID> /bin/bash
pip install aiohttp==3.9.1 outlines==0.0.37 openai==1.23.3 -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
```
`Tips:若在K100/Z100L上使用,需要替换flash_attn,下载链接:https://forum.hpccube.com/thread/515`
### Dockerfile(方法二)
```
......@@ -56,6 +59,7 @@ docker run -it --name chatglm_vllm --privileged --shm-size=64G --device=/dev/kf
docker build -t chatglm:latest .
docker run -it --name chatglm_vllm --privileged --shm-size=64G --device=/dev/kfd --device=/dev/dri/ --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --ulimit memlock=-1:-1 --ipc=host --network host --group-add video -v /opt/hyhal:/opt/hyhal -v <Host Path>:<Container Path> llama:latest /bin/bash
```
`Tips:若在K100/Z100L上使用,需要替换flash_attn,下载链接:https://forum.hpccube.com/thread/515`
### Anaconda(方法三)
```
......@@ -71,7 +75,7 @@ pip install aiohttp==3.9.1 outlines==0.0.37 openai==1.23.3
* flash_attn: 2.0.4
* python: python3.10
`Tips:以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应.目前只能在K100_AI上使用`
`Tips:若在K100/Z100L上使用,需要替换flash_attn,下载链接:https://forum.hpccube.com/thread/515`
## 数据集
......
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