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
textmonkey_pytorch
Commits
18affba2
"git@developer.sourcefind.cn:yangql/composable_kernel-1.git" did not exist on "a9a392b44dd53a4c29561b601c4ac194880ab45a"
Unverified
Commit
18affba2
authored
Mar 07, 2024
by
echo840
Committed by
GitHub
Mar 07, 2024
Browse files
Update README_cn.md
parent
3914a1da
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
README_cn.md
README_cn.md
+1
-1
No files found.
README_cn.md
View file @
18affba2
...
@@ -140,7 +140,7 @@ Monkey训练使用的json文件可以在[链接](https://drive.google.com/file/d
...
@@ -140,7 +140,7 @@ Monkey训练使用的json文件可以在[链接](https://drive.google.com/file/d
受 Qwen-VL 的启发,我们冻结了大型语言模型(LLM),并将 LoRA 引入四个线性层
```"c_attn"、"attn.c_proj"、"w1"、"w2"```
进行训练。 这使得使用 8 个 NVIDIA 3090 GPU 训练 Monkey 成为可能。
受 Qwen-VL 的启发,我们冻结了大型语言模型(LLM),并将 LoRA 引入四个线性层
```"c_attn"、"attn.c_proj"、"w1"、"w2"```
进行训练。 这使得使用 8 个 NVIDIA 3090 GPU 训练 Monkey 成为可能。
-
添加LoRA:需要将
```model_qwen.py```
的内容替换为
```model_qwen_nvdia3090.py```
的内容
-
添加LoRA:需要将
```model
ing
_qwen.py```
的内容替换为
```model
ing
_qwen_nvdia3090.py```
的内容
-
冻结LLM:需要在
```finetune_multitask.py```
中冻结除LoRA和Resampler模块的其他模块
-
冻结LLM:需要在
```finetune_multitask.py```
中冻结除LoRA和Resampler模块的其他模块
## 推理
## 推理
...
...
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