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
llama3_pytorch
Commits
f7684949
Commit
f7684949
authored
Apr 20, 2024
by
Rayyyyy
Browse files
add download infos of 70B in README
parent
1c339d9a
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
44 additions
and
6 deletions
+44
-6
README.md
README.md
+44
-6
No files found.
README.md
View file @
f7684949
...
...
@@ -27,6 +27,7 @@ pip install -e .
### Dockerfile(方法二)
```
bash
cd
docker
docker build
--no-cache
-t
llama3:latest
.
docker run
-it
-v
/path/your_code_data/:/path/your_code_data/
-v
/opt/hyhal/:/opt/hyhal/:ro
--shm-size
=
32G
--privileged
=
true
--device
=
/dev/kfd
--device
=
/dev/dri/
--group-add
video
--name
docker_name imageID bash
...
...
@@ -65,7 +66,7 @@ pip install -e .
所有模型都支持序列长度高达8192个tokens,但我们根据max_seq_len和max_batch_size值预先分配缓存。根据你的硬件设置。
**Tips:**
-
`–nproc_per_node`
需要根据模型的MP值进行设置。
-
`–nproc_per_node`
需要根据模型的MP值进行设置
(参考上表)
。
-
`max_seq_len`
和
`max_batch_size`
参数按需设置。
### Pretrained模型
...
...
@@ -126,29 +127,66 @@ export HF_ENDPOINT=https://hf-mirror.com
```
2.
预训练模型下载,
**token**
参数通过huggingface账号获取
-
Meta-Llama-3-8B 模型
```
bash
mkdir
Meta-Llama-3-8B
huggingface-cli download meta-llama/Meta-Llama-3-8B
--include
"original/*"
--local-dir
Meta-Llama-3-8B
--token
hf_
*
```
-
Meta-Llama-3-8B-Instruct 模型
```
bash
mkdir
Meta-Llama-3-8B-Instruct
huggingface-cli download
--resume-download
meta-llama/Meta-Llama-3-8B-Instruct
--include
"original/*"
--local-dir
Meta-Llama-3-8B-Instruct
--token
hf_
*
huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct
--include
"original/*"
--local-dir
Meta-Llama-3-8B-Instruct
--token
hf_
*
```
-
Meta-Llama-3-
8
B 模型
-
Meta-Llama-3-
70
B 模型
```
bash
mkdir
Meta-Llama-3-8B
huggingface-cli download
--resume-download
meta-llama/Meta-Llama-3-8B
--include
"original/*"
--local-dir
Meta-Llama-3-8B
--token
hf_
*
mkdir
Meta-Llama-3-70B
huggingface-cli download meta-llama/Meta-Llama-3-70B
--include
"original/*"
--local-dir
Meta-Llama-3-70B
--token
hf_
*
```
-
Meta-Llama-3-70B-Instruct 模型
```
bash
mkdir
Meta-Llama-3-70B-Instruct
huggingface-cli download meta-llama/Meta-Llama-3-70B-Instruct
--include
"original/*"
--local-dir
Meta-Llama-3-70B-Instruct
--token
hf_
*
```
模型目录结构如下:
```
bash
├── llama3_pytorch
│ ├── Meta-Llama-3-8B
│ ├── original
│ ├── consolidated.00.pth
│ ├── params.json
│ └── tokenizer.model
│ ├── Meta-Llama-3-8B-Instruct
│ ├── original
│ ├── consolidated.00.pth
│ ├── params.json
│ └── tokenizer.model
│ ├── Meta-Llama-3-8B
│ ├── Meta-Llama-3-70B
│ ├── original
│ ├── consolidated.00.pth
│ ├── consolidated.01.pth
│ ├── consolidated.02.pth
│ ├── consolidated.03.pth
│ ├── consolidated.04.pth
│ ├── consolidated.05.pth
│ ├── consolidated.06.pth
│ ├── consolidated.07.pth
│ ├── params.json
│ └── tokenizer.model
│ ├── Meta-Llama-3-70B-Instruct
│ ├── original
│ ├── consolidated.00.pth
│ ├── consolidated.01.pth
│ ├── consolidated.02.pth
│ ├── consolidated.03.pth
│ ├── consolidated.04.pth
│ ├── consolidated.05.pth
│ ├── consolidated.06.pth
│ ├── consolidated.07.pth
│ ├── params.json
│ └── tokenizer.model
```
...
...
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