Skip to content

fix OpenXLab #28

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vansin merged 15 commits into from
Dec 31, 2023
Merged

fix OpenXLab #28

Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
62255d3
update hello-world
KMnO4-zx Dec 13, 2023
d82ae3c
fix hello_world
KMnO4-zx Dec 13, 2023
fb607f6
Fix capitalization of Hugging Face and Modelscope in documentation
KMnO4-zx Dec 13, 2023
6655d9b
Fix typo in ModelScope heading
KMnO4-zx Dec 13, 2023
c096b9f
Fix typos and update links in hello_world.md
KMnO4-zx Dec 13, 2023
af12d46
Update Lagent framework and fix typos
KMnO4-zx Dec 13, 2023
45b6656
update head img
KMnO4-zx Dec 14, 2023
da56a3a
Merge branch 'InternLM:main' into main
KMnO4-zx Dec 26, 2023
c9254ae
Update hello_world.md with new title and image
KMnO4-zx Dec 26, 2023
714451a
Update demo titles and descriptions
KMnO4-zx Dec 26, 2023
9e23559
Merge branch 'InternLM:main' into main
KMnO4-zx Dec 26, 2023
07d3a04
Add demos for intelligent conversation and tool invocation using Inte…
KMnO4-zx Dec 26, 2023
6216d6d
Merge branch 'main' of https://github.com/KMnO4-zx/tutorial
KMnO4-zx Dec 26, 2023
cb8ba08
Fix typo in OpenXLab section
KMnO4-zx Dec 28, 2023
dc0b598
update 端口说明
KMnO4-zx Dec 28, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion helloworld/hello_world.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,8 @@

## 2. InternLM-Chat-7B 智能对话 Demo

本小节我们将使用[InternStudio](https://studio.intern-ai.org.cn/)中的 A100(1/4) 机器和`InternLM-Chat-7B`模型部署一个智能对话 Demo。

### 2.1 环境准备

在[InternStudio](https://studio.intern-ai.org.cn/)平台中选择 A100(1/4) 的配置，如下图所示镜像选择`Cuda11.7-conda`，如下图所示：
Expand Down Expand Up @@ -168,6 +170,8 @@ streamlit run web_demo.py --server.address 127.0.0.1 --server.port 6006

## 3. Lagent 智能体工具调用 Demo

本小节我们将使用[InternStudio](https://studio.intern-ai.org.cn/)中的 A100(1/4) 机器、`InternLM-Chat-7B`模型和`Lagent`框架部署一个智能工具调用 Demo。

Lagent 是一个轻量级、开源的基于大语言模型的智能体（agent）框架，支持用户快速地将一个大语言模型转变为多种类型的智能体，并提供了一些典型工具为大语言模型赋能。通过 Lagent 框架可以更好的发挥 InternLM 的全部性能。

下面我们就开始动手实现！
Expand Down Expand Up @@ -455,6 +459,8 @@ streamlit run /root/code/lagent/examples/react_web_demo.py --server.address 127.

## 4. 浦语·灵笔图文理解创作 Demo

本小节我们将使用[InternStudio](https://studio.intern-ai.org.cn/)中的 A100(1/4) * 2 机器和`internlm-xcomposer-7b`模型部署一个图文理解创作 Demo 。

### 4.1 环境准备

首先在 [InternStudio](https://studio.intern-ai.org.cn/) 上选择A100(1/4)*2的配置。如下图所示：
Expand Down Expand Up @@ -598,6 +604,8 @@ EOF

### 5.2 配置本地端口

在本地配置端口，可以通过`ssh`连接到服务器，然后将服务器的端口映射到本地，这样就可以在本地浏览器中访问服务器的端口了。

首先我们需要配置一下本地的 `SSH Key` ，我们这里以`Windows`为例。

步骤①：在本地机器上打开`Power Shell`终端。在终端中，运行以下命令来生成SSH密钥对：（如下图所示）
Expand Down Expand Up @@ -678,7 +686,7 @@ import os
model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm-chat-7b', cache_dir='your path', revision='master')
```

#### 5.3.3 OpenXlab
#### 5.3.3 OpenXLab

OpenXLab 可以通过指定模型仓库的地址，以及需要下载的文件的名称，文件所需下载的位置等，直接下载模型权重文件。

Expand Down