Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
Llama1and2_lmdeploy
Commits
256b9064
Commit
256b9064
authored
Nov 30, 2023
by
xiabo
Browse files
update submodule
parent
316b0607
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
14 additions
and
2 deletions
+14
-2
.gitmodules
.gitmodules
+1
-1
README.md
README.md
+3
-1
model.properties
model.properties
+10
-0
No files found.
.gitmodules
View file @
256b9064
[submodule "lmdeploy"]
path = lmdeploy
url = http://developer.hpccube.com/codes/aicomponent/lmdeploy.git
branch = develop
\ No newline at end of file
tag = dtk23.04-v0.0.13
\ No newline at end of file
README.md
View file @
256b9064
# LLama
_lmdeploy
# LLama
## 论文
-
[
https://arxiv.org/pdf/2302.13971.pdf
](
https://arxiv.org/pdf/2302.13971.pdf
)
...
...
@@ -33,6 +33,8 @@ docker run -it --name llama --shm-size=1024G --device=/dev/kfd --device=/dev/dr
## 数据集
无
## 推理
### 源码编译安装
```
# 若使用光源的镜像,可以跳过源码编译安装,镜像里面安装好了lmdeploy。
...
...
model.properties
0 → 100644
View file @
256b9064
# 模型唯一标识
modelCode
=
457
# 模型名称
modelName
=
llama_lmdeploy
# 模型描述
modelDescription
=
LLama是一个基础语言模型的集合,参数范围从7B到65B。在数万亿的tokens上训练出的模型,并表明可以专门使用公开可用的数据集来训练最先进的模型。
# 应用场景
appScenario
=
推理,对话问答,金融,科研,教育
# 框架类型
frameType
=
lmdeploy
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment