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
DeepSeek-OCR-2_pytorch
Commits
950e705c
Commit
950e705c
authored
Feb 04, 2026
by
chenych
Browse files
Update README
parent
5c14fb01
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
3 additions
and
2 deletions
+3
-2
README.md
README.md
+2
-1
model.properties
model.properties
+1
-1
No files found.
README.md
View file @
950e705c
...
@@ -63,6 +63,7 @@ python DeepSeek-OCR2-hf/run_dpsk_ocr2.py --model_name_or_path=deepseek-ai/DeepSe
...
@@ -63,6 +63,7 @@ python DeepSeek-OCR2-hf/run_dpsk_ocr2.py --model_name_or_path=deepseek-ai/DeepSe
```
```
### vllm
### vllm
#### 单机推理
> 模型地址,测试图片路径,输出路径请根据实际情况在`DeepSeek-OCR2-vllm/config.py`中修改。
> 模型地址,测试图片路径,输出路径请根据实际情况在`DeepSeek-OCR2-vllm/config.py`中修改。
```
bash
```
bash
export
VLLM_USE_V1
=
0
export
VLLM_USE_V1
=
0
...
@@ -80,7 +81,7 @@ python DeepSeek-OCR2-vllm/run_dpsk_ocr2_image.py
...
@@ -80,7 +81,7 @@ python DeepSeek-OCR2-vllm/run_dpsk_ocr2_image.py
</div>
</div>
### 精度
### 精度
DCU与GPU精度一致,推理框架:vllm。
DCU与GPU精度一致,推理框架:
transformers,
vllm。
## 预训练权重
## 预训练权重
| 模型名称 | 权重大小 | DCU型号 | 最低卡数需求 |下载地址|
| 模型名称 | 权重大小 | DCU型号 | 最低卡数需求 |下载地址|
...
...
model.properties
View file @
950e705c
...
@@ -3,7 +3,7 @@ modelCode=2003
...
@@ -3,7 +3,7 @@ modelCode=2003
# 模型名称
# 模型名称
modelName
=
deepseek-ocr-2_pytorch
modelName
=
deepseek-ocr-2_pytorch
# 模型描述
# 模型描述
modelDescription
=
DeepSeek-OCR
2 通过引入 DeepEncoder V2 架构,实现了视觉编码从「固定扫描」向「语义推理」的范式转变!
modelDescription
=
DeepSeek-OCR
-
2 通过引入 DeepEncoder V2 架构,实现了视觉编码从「固定扫描」向「语义推理」的范式转变!
# 运行过程
# 运行过程
processType
=
推理
processType
=
推理
# 算法类别
# 算法类别
...
...
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