Submmit documents of internLM #134
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
go-with-me000
force-pushed
the
cky/document_of_internLM
branch
from
074519b
to
a21d6bf
Compare
gaotongxiao
reviewed
Jul 31, 2023
docs/zh_cn/get_started.md
Outdated
| @@ -55,6 +55,52 @@ | |||
|
|
|||
| </details> | |||
|
|
|||
| 5. 安装 InternLM（可选）： | |||
|
|
|||
| 评测**InternLM**模型，可以按照我们提供的样例并遵循如下步骤。 | |||
There was a problem hiding this comment.
Suggested change
| 评测**InternLM**模型，可以按照我们提供的样例并遵循如下步骤。 | |
| 如果需要运行原生 **InternLM** 模型（非 Huggingface 版），可以按照我们提供的样例并遵循如下步骤。 |
| 在你的根目录下安装该库 | ||
|
|
||
| ```bash | ||
| git clone https://gitlab.pjlab.org.cn/chenkeyu1/internlm-lite.git |
docs/zh_cn/get_started.md
Outdated
Comment on lines
65
to
66
| 安装InternLM-Lite | ||
| 在你的根目录下安装该库 |
There was a problem hiding this comment.
Suggested change
| 安装InternLM-Lite | |
| 在你的根目录下安装该库 | |
| 安装 InternLM-Lite。在你的根目录下安装该库： |
docs/zh_cn/get_started.md
Outdated
Comment on lines
73
to
91
| 之后，可以建立一个软链接，用于关联模型权重等文件至你指定的文件夹下，例如在`configs/models/internlm_7b.py`中的**internData** | ||
|
|
||
| ```bash | ||
| ln -s /path/data ./internData | ||
| ``` | ||
|
|
||
| 自然，也可以提供绝对路径而不是软链接的形式，这样更简单。（模型权重也就是**path**参数只需给出权重所在的目录即可，其余两者需直接给出完整路径） | ||
| 这里，你需要提供三种文件: | ||
|
|
||
| - 模型权重 | ||
| - 模型配置 | ||
| - **Tokenizer** | ||
| 目前开源的模型权重为InternLM-7b，网址：[Models-OpenXLab](https://openxlab.org.cn/models/detail/OpenLMLab/InternLM-7b)，下载代码为 | ||
|
|
||
| ```bash | ||
| wegt https://download.openxlab.org.cn/models/OpenLMLab/InternLM-7b/weight/model_tp0_pp0.pt | ||
| ``` | ||
|
|
||
| 后两种文件在InternLM-Lite库中的data文件夹下，完整的config配置如下： |
There was a problem hiding this comment.
教程应该按操作流程一步步写，忽略不太重要的细节。另外文档有些混乱，建议按照下面的逻辑组织文档：
下载 internlm-lite -> 进入 data 文件夹 -> wget 下载模型权重 -> 回到 opencompass 目录，把 internlm-lite/data 文件夹软链到 internData -> 准备配置
|
Closing this PR as it is way out of dated. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Submmit documents of internLM