Skip to content

docs: 添加 llama.cpp 关于 tokenize 错误的解决方案说明 #17729

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
megemini wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: 添加 llama.cpp 关于 tokenize 错误的解决方案说明 #17729

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions docs/version3.x/pipeline_usage/PaddleOCR-VL.en.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1634,6 +1634,18 @@ The parameters supported by this command are as follows:
--host 0.0.0.0 \
--temp 0
```
> TIP:
>
> If encountering the error `tokenize: error: number of bitmaps (1) does not match number of markers (0).`, you can use the `--chat-template-file` parameter to specify the template file. For example:
> ```shell
> ./build/bin/llama-server \
> -m /path/to/PaddleOCR-VL-1.5-GGUF.gguf \
> --mmproj /path/to/PaddleOCR-VL-1.5-GGUF-mmproj.gguf \
> --port 8111 \
> --host 0.0.0.0 \
> --temp 0 \
> --chat-template-file /path/to/chat_template_llama.jinja
> ```

### 3.2 Client Usage Methods

Expand Down
12 changes: 12 additions & 0 deletions docs/version3.x/pipeline_usage/PaddleOCR-VL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1613,6 +1613,18 @@ paddleocr genai_server --model_name PaddleOCR-VL-1.5-0.9B --backend vllm --port
--host 0.0.0.0 \
--temp 0
```
> TIP:
>
> 如果出现错误 `tokenize: error: number of bitmaps (1) does not match number of markers (0).`，可以使用 `--chat-template-file` 参数指定模板文件。比如：
> ```shell
> ./build/bin/llama-server \
> -m /path/to/PaddleOCR-VL-1.5-GGUF.gguf \
> --mmproj /path/to/PaddleOCR-VL-1.5-GGUF-mmproj.gguf \
> --port 8111 \
> --host 0.0.0.0 \
> --temp 0 \
> --chat-template-file /path/to/chat_template_llama.jinja
> ```

</details>

Expand Down