diff --git a/docs/version3.x/pipeline_usage/PaddleOCR-VL.en.md b/docs/version3.x/pipeline_usage/PaddleOCR-VL.en.md
index 6bacf4591e8..cac4cda0d24 100644
--- a/docs/version3.x/pipeline_usage/PaddleOCR-VL.en.md
+++ b/docs/version3.x/pipeline_usage/PaddleOCR-VL.en.md
@@ -1636,6 +1636,18 @@ 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
 
diff --git a/docs/version3.x/pipeline_usage/PaddleOCR-VL.md b/docs/version3.x/pipeline_usage/PaddleOCR-VL.md
index 69eb4d8cf86..4e56147019b 100644
--- a/docs/version3.x/pipeline_usage/PaddleOCR-VL.md
+++ b/docs/version3.x/pipeline_usage/PaddleOCR-VL.md
@@ -1615,6 +1615,18 @@ 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>