PaddlePaddle · cuicheng01 · Nov 8, 2024 · Nov 8, 2024
diff --git a/README.md b/README.md
@@ -595,7 +595,7 @@ for res in output:
   <summary> <b> 🖼️ 图像分类 </b></summary>
 
   * [📂 图像分类模块使用教程](https://paddlepaddle.github.io/PaddleX/latest/module_usage/tutorials/cv_modules/image_classification.html)
-  * [🏷️ 图像多标签分类模块使用教程](https://paddlepaddle.github.io/PaddleX/latest/module_usage/tutorials/cv_modules/ml_classification.html)
+  * [🏷️ 图像多标签分类模块使用教程](https://paddlepaddle.github.io/PaddleX/latest/module_usage/tutorials/cv_modules/image_multilabel_classification.html)
   * [👤 行人属性识别模块使用教程](https://paddlepaddle.github.io/PaddleX/latest/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.html)
   * [🚗 车辆属性识别模块使用教程](https://paddlepaddle.github.io/PaddleX/latest/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.html)
 

diff --git a/README_en.md b/README_en.md
@@ -586,7 +586,7 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
   <summary> <b> 🖼️ Image Classification </b></summary>
 
   * [📂 Image Classification Module Tutorial](https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/cv_modules/image_classification.html)
-  * [🏷️ Multi-label Image Classification Module Tutorial](https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/cv_modules/ml_classification.html)
+  * [🏷️ Multi-label Image Classification Module Tutorial](https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/cv_modules/image_multilabel_classification.html)
 
   * [👤 Pedestrian Attribute Recognition Module Tutorial](https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.html)
   * [🚗 Vehicle Attribute Recognition Module Tutorial](https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.html)

diff --git a/docs/index.en.md b/docs/index.en.md
diff --git a/docs/index.md b/docs/index.md
diff --git a/...orials/cv_modules/ml_classification.en.md → ...les/image_multilabel_classification.en.md b/...orials/cv_modules/ml_classification.en.md → ...les/image_multilabel_classification.en.md
diff --git a/...tutorials/cv_modules/ml_classification.md → ...odules/image_multilabel_classification.md b/...tutorials/cv_modules/ml_classification.md → ...odules/image_multilabel_classification.md
diff --git a/docs/pipeline_deploy/high_performance_inference.en.md b/docs/pipeline_deploy/high_performance_inference.en.md
@@ -158,25 +158,22 @@ PaddleX provides default high-performance inference configurations for each mode
   <tr>
     <td>General Image Classification</td>
     <td>Image Classification</td>
-    <td>ResNet18<br/>ResNet34<details><summary><b>more</b></summary>
-<p>ResNet50ResNet101ResNet152ResNet18_vdResNet34_vdResNet50_vdResNet101_vdResNet152_vdResNet200_vdPP-LCNet_x0_25PP-LCNet_x0_35PP-LCNet_x0_5PP-LCNet_x0_75PP-LCNet_x1_0PP-LCNet_x1_5PP-LCNet_x2_0PP-LCNet_x2_5PP-LCNetV2_smallPP-LCNetV2_basePP-LCNetV2_largeMobileNetV3_large_x0_35MobileNetV3_large_x0_5MobileNetV3_large_x0_75MobileNetV3_large_x1_0MobileNetV3_large_x1_25MobileNetV3_small_x0_35MobileNetV3_small_x0_5MobileNetV3_small_x0_75MobileNetV3_small_x1_0MobileNetV3_small_x1_25ConvNeXt_tinyConvNeXt_smallConvNeXt_base_224ConvNeXt_base_384ConvNeXt_large_224ConvNeXt_large_384MobileNetV1_x0_25MobileNetV1_x0_5MobileNetV1_x0_75MobileNetV1_x1_0MobileNetV2_x0_25MobileNetV2_x0_5MobileNetV2_x1_0MobileNetV2_x1_5MobileNetV2_x2_0SwinTransformer_tiny_patch4_window7_224SwinTransformer_small_patch4_window7_224SwinTransformer_base_patch4_window7_224SwinTransformer_base_patch4_window12_384SwinTransformer_large_patch4_window7_224SwinTransformer_large_patch4_window12_384PP-HGNet_smallPP-HGNet_tinyPP-HGNet_basePP-HGNetV2-B0PP-HGNetV2-B1PP-HGNetV2-B2PP-HGNetV2-B3PP-HGNetV2-B4PP-HGNetV2-B5PP-HGNetV2-B6CLIP_vit_base_patch16_224CLIP_vit_large_patch14_224</p>
-<p><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/></p></details></td>
+    <td>ResNet18<br/>ResNet34<details>
+    <summary><b>more</b></summary>ResNet50<br/>ResNet101<br/>ResNet152<br/>ResNet18_vd<br/>ResNet34_vd<br/>ResNet50_vd<br/>ResNet101_vd<br/>ResNet152_vd<br/>ResNet200_vd<br/>PP-LCNet_x0_25<br/>PP-LCNet_x0_35<br/>PP-LCNet_x0_5<br/>PP-LCNet_x0_75<br/>PP-LCNet_x1_0<br/>PP-LCNet_x1_5<br/>PP-LCNet_x2_0<br/>PP-LCNet_x2_5<br/>PP-LCNetV2_small<br/>PP-LCNetV2_base<br/>PP-LCNetV2_large<br/>MobileNetV3_large_x0_35<br/>MobileNetV3_large_x0_5<br/>MobileNetV3_large_x0_75<br/>MobileNetV3_large_x1_0<br/>MobileNetV3_large_x1_25<br/>MobileNetV3_small_x0_35<br/>MobileNetV3_small_x0_5<br/>MobileNetV3_small_x0_75<br/>MobileNetV3_small_x1_0<br/>MobileNetV3_small_x1_25<br/>ConvNeXt_tiny<br/>ConvNeXt_small<br/>ConvNeXt_base_224<br/>ConvNeXt_base_384<br/>ConvNeXt_large_224<br/>ConvNeXt_large_384<br/>MobileNetV1_x0_25<br/>MobileNetV1_x0_5<br/>MobileNetV1_x0_75<br/>MobileNetV1_x1_0<br/>MobileNetV2_x0_25<br/>MobileNetV2_x0_5<br/>MobileNetV2_x1_0<br/>MobileNetV2_x1_5<br/>MobileNetV2_x2_0<br/>SwinTransformer_tiny_patch4_window7_224<br/>SwinTransformer_small_patch4_window7_224<br/>SwinTransformer_base_patch4_window7_224<br/>SwinTransformer_base_patch4_window12_384<br/>SwinTransformer_large_patch4_window7_224<br/>SwinTransformer_large_patch4_window12_384<br/>PP-HGNet_small<br/>PP-HGNet_tiny<br/>PP-HGNet_base<br/>PP-HGNetV2-B0<br/>PP-HGNetV2-B1<br/>PP-HGNetV2-B2<br/>PP-HGNetV2-B3<br/>PP-HGNetV2-B4<br/>PP-HGNetV2-B5<br/>PP-HGNetV2-B6<br/>CLIP_vit_base_patch16_224<br/>CLIP_vit_large_patch14_224</details></td>
   </tr>
 
   <tr>
     <td>General Object Detection</td>
     <td>Object Detection</td>
-    <td>PP-YOLOE_plus-S<br/>PP-YOLOE_plus-M<details><summary><b>more</b></summary>
-<p>PP-YOLOE_plus-LPP-YOLOE_plus-XYOLOX-NYOLOX-TYOLOX-SYOLOX-MYOLOX-LYOLOX-XYOLOv3-DarkNet53YOLOv3-ResNet50_vd_DCNYOLOv3-MobileNetV3RT-DETR-R18RT-DETR-R50RT-DETR-LRT-DETR-HRT-DETR-XPicoDet-SPicoDet-L</p>
-<p><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/></p></details></td>
+    <td>PP-YOLOE_plus-S<br/>PP-YOLOE_plus-M<details>
+        <summary><b>more</b></summary>PP-YOLOE_plus-L<br/>PP-YOLOE_plus-X<br/>YOLOX-N<br/>YOLOX-T<br/>YOLOX-S<br/>YOLOX-M<br/>YOLOX-L<br/>YOLOX-X<br/>YOLOv3-DarkNet53<br/>YOLOv3-ResNet50_vd_DCN<br/>YOLOv3-MobileNetV3<br/>RT-DETR-R18<br/>RT-DETR-R50<br/>RT-DETR-L<br/>RT-DETR-H<br/>RT-DETR-X<br/>PicoDet-S<br/>PicoDet-L</details></td>
   </tr>
 
   <tr>
     <td>General Semantic Segmentation</td>
     <td>Semantic Segmentation</td>
-    <td>Deeplabv3-R50<br/>Deeplabv3-R101<details><summary><b>more</b></summary>
-<p>Deeplabv3_Plus-R50Deeplabv3_Plus-R101PP-LiteSeg-TOCRNet_HRNet-W48OCRNet_HRNet-W18SeaFormer_tinySeaFormer_smallSeaFormer_baseSeaFormer_largeSegFormer-B0SegFormer-B1SegFormer-B2SegFormer-B3SegFormer-B4SegFormer-B5</p>
-<p><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/></p></details></td>
+    <td>Deeplabv3-R50<br/>Deeplabv3-R101<details>
+    <summary><b>more</b></summary>Deeplabv3_Plus-R50<br/>Deeplabv3_Plus-R101<br/>PP-LiteSeg-T<br/>OCRNet_HRNet-W48<br/>OCRNet_HRNet-W18<br/>SeaFormer_tiny<br/>SeaFormer_small<br/>SeaFormer_base<br/>SeaFormer_large<br/>SegFormer-B0<br/>SegFormer-B1<br/>SegFormer-B2<br/>SegFormer-B3<br/>SegFormer-B4<br/>SegFormer-B5</details></td>
   </tr>
 
   <tr>
@@ -188,9 +185,8 @@ PaddleX provides default high-performance inference configurations for each mode
   <tr>
     <td rowspan="3">Seal Text Recognition</td>
     <td>Layout Analysis</td>
-    <td>PicoDet-S_layout_3cls<br/>PicoDet-S_layout_17cls<details><summary><b>more</b></summary>
-<p>PicoDet-L_layout_3clsPicoDet-L_layout_17clsRT-DETR-H_layout_3clsRT-DETR-H_layout_17cls</p>
-<p><br/><br/><br/></p></details></td>
+    <td>PicoDet-S_layout_3cls<br/>PicoDet-S_layout_17cls<details>
+    <summary><b>more</b></summary>PicoDet-L_layout_3cls<br/>PicoDet-L_layout_17cls<br/>RT-DETR-H_layout_3cls<br/>RT-DETR-H_layout_17cls</details></td>
   </tr>
 
   <tr>

diff --git a/docs/pipeline_deploy/high_performance_inference.md b/docs/pipeline_deploy/high_performance_inference.md
@@ -155,26 +155,23 @@ PaddleX 为每个模型提供默认的高性能推理配置，并将其存储在
   <tr>
     <td>通用图像分类</td>
     <td>图像分类</td>
-    <td>ResNet18<br/>ResNet34<details><summary><b>more</b></summary>
-<p>ResNet50ResNet101ResNet152ResNet18_vdResNet34_vdResNet50_vdResNet101_vdResNet152_vdResNet200_vdPP-LCNet_x0_25PP-LCNet_x0_35PP-LCNet_x0_5PP-LCNet_x0_75PP-LCNet_x1_0PP-LCNet_x1_5PP-LCNet_x2_0PP-LCNet_x2_5PP-LCNetV2_smallPP-LCNetV2_basePP-LCNetV2_largeMobileNetV3_large_x0_35MobileNetV3_large_x0_5MobileNetV3_large_x0_75MobileNetV3_large_x1_0MobileNetV3_large_x1_25MobileNetV3_small_x0_35MobileNetV3_small_x0_5MobileNetV3_small_x0_75MobileNetV3_small_x1_0MobileNetV3_small_x1_25ConvNeXt_tinyConvNeXt_smallConvNeXt_base_224ConvNeXt_base_384ConvNeXt_large_224ConvNeXt_large_384MobileNetV1_x0_25MobileNetV1_x0_5MobileNetV1_x0_75MobileNetV1_x1_0MobileNetV2_x0_25MobileNetV2_x0_5MobileNetV2_x1_0MobileNetV2_x1_5MobileNetV2_x2_0SwinTransformer_tiny_patch4_window7_224SwinTransformer_small_patch4_window7_224SwinTransformer_base_patch4_window7_224SwinTransformer_base_patch4_window12_384SwinTransformer_large_patch4_window7_224SwinTransformer_large_patch4_window12_384PP-HGNet_smallPP-HGNet_tinyPP-HGNet_basePP-HGNetV2-B0PP-HGNetV2-B1PP-HGNetV2-B2PP-HGNetV2-B3PP-HGNetV2-B4PP-HGNetV2-B5PP-HGNetV2-B6CLIP_vit_base_patch16_224CLIP_vit_large_patch14_224</p>
-<p><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/></p></details></td>
+    <td>ResNet18<br/>ResNet34<details>
+    <summary><b>more</b></summary>ResNet50<br/>ResNet101<br/>ResNet152<br/>ResNet18_vd<br/>ResNet34_vd<br/>ResNet50_vd<br/>ResNet101_vd<br/>ResNet152_vd<br/>ResNet200_vd<br/>PP-LCNet_x0_25<br/>PP-LCNet_x0_35<br/>PP-LCNet_x0_5<br/>PP-LCNet_x0_75<br/>PP-LCNet_x1_0<br/>PP-LCNet_x1_5<br/>PP-LCNet_x2_0<br/>PP-LCNet_x2_5<br/>PP-LCNetV2_small<br/>PP-LCNetV2_base<br/>PP-LCNetV2_large<br/>MobileNetV3_large_x0_35<br/>MobileNetV3_large_x0_5<br/>MobileNetV3_large_x0_75<br/>MobileNetV3_large_x1_0<br/>MobileNetV3_large_x1_25<br/>MobileNetV3_small_x0_35<br/>MobileNetV3_small_x0_5<br/>MobileNetV3_small_x0_75<br/>MobileNetV3_small_x1_0<br/>MobileNetV3_small_x1_25<br/>ConvNeXt_tiny<br/>ConvNeXt_small<br/>ConvNeXt_base_224<br/>ConvNeXt_base_384<br/>ConvNeXt_large_224<br/>ConvNeXt_large_384<br/>MobileNetV1_x0_25<br/>MobileNetV1_x0_5<br/>MobileNetV1_x0_75<br/>MobileNetV1_x1_0<br/>MobileNetV2_x0_25<br/>MobileNetV2_x0_5<br/>MobileNetV2_x1_0<br/>MobileNetV2_x1_5<br/>MobileNetV2_x2_0<br/>SwinTransformer_tiny_patch4_window7_224<br/>SwinTransformer_small_patch4_window7_224<br/>SwinTransformer_base_patch4_window7_224<br/>SwinTransformer_base_patch4_window12_384<br/>SwinTransformer_large_patch4_window7_224<br/>SwinTransformer_large_patch4_window12_384<br/>PP-HGNet_small<br/>PP-HGNet_tiny<br/>PP-HGNet_base<br/>PP-HGNetV2-B0<br/>PP-HGNetV2-B1<br/>PP-HGNetV2-B2<br/>PP-HGNetV2-B3<br/>PP-HGNetV2-B4<br/>PP-HGNetV2-B5<br/>PP-HGNetV2-B6<br/>CLIP_vit_base_patch16_224<br/>CLIP_vit_large_patch14_224</details></td>
   </tr>
 
 
   <tr>
     <td>通用目标检测</td>
     <td>目标检测</td>
-    <td>PP-YOLOE_plus-S<br/>PP-YOLOE_plus-M<details><summary><b>more</b></summary>
-<p>PP-YOLOE_plus-LPP-YOLOE_plus-XYOLOX-NYOLOX-TYOLOX-SYOLOX-MYOLOX-LYOLOX-XYOLOv3-DarkNet53YOLOv3-ResNet50_vd_DCNYOLOv3-MobileNetV3RT-DETR-R18RT-DETR-R50RT-DETR-LRT-DETR-HRT-DETR-XPicoDet-SPicoDet-L</p>
-<p><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/></p></details></td>
+    <td>PP-YOLOE_plus-S<br/>PP-YOLOE_plus-M<details>
+        <summary><b>more</b></summary>PP-YOLOE_plus-L<br/>PP-YOLOE_plus-X<br/>YOLOX-N<br/>YOLOX-T<br/>YOLOX-S<br/>YOLOX-M<br/>YOLOX-L<br/>YOLOX-X<br/>YOLOv3-DarkNet53<br/>YOLOv3-ResNet50_vd_DCN<br/>YOLOv3-MobileNetV3<br/>RT-DETR-R18<br/>RT-DETR-R50<br/>RT-DETR-L<br/>RT-DETR-H<br/>RT-DETR-X<br/>PicoDet-S<br/>PicoDet-L</details></td>
   </tr>
 
   <tr>
     <td>通用语义分割</td>
     <td>语义分割</td>
-    <td>Deeplabv3-R50<br/>Deeplabv3-R101<details><summary><b>more</b></summary>
-<p>Deeplabv3_Plus-R50Deeplabv3_Plus-R101PP-LiteSeg-TOCRNet_HRNet-W48OCRNet_HRNet-W18SeaFormer_tinySeaFormer_smallSeaFormer_baseSeaFormer_largeSegFormer-B0SegFormer-B1SegFormer-B2SegFormer-B3SegFormer-B4SegFormer-B5</p>
-<p><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/></p></details></td>
+    <td>Deeplabv3-R50<br/>Deeplabv3-R101<details>
+    <summary><b>more</b></summary>Deeplabv3_Plus-R50<br/>Deeplabv3_Plus-R101<br/>PP-LiteSeg-T<br/>OCRNet_HRNet-W48<br/>OCRNet_HRNet-W18<br/>SeaFormer_tiny<br/>SeaFormer_small<br/>SeaFormer_base<br/>SeaFormer_large<br/>SegFormer-B0<br/>SegFormer-B1<br/>SegFormer-B2<br/>SegFormer-B3<br/>SegFormer-B4<br/>SegFormer-B5</details></td>
   </tr>
 
   <tr>
@@ -197,9 +194,8 @@ PaddleX 为每个模型提供默认的高性能推理配置，并将其存储在
   <tr>
     <td rowspan="3">印章文本识别</td>
     <td>版面区域分析</td>
-    <td>PicoDet-S_layout_3cls<br/>PicoDet-S_layout_17cls<details><summary><b>more</b></summary>
-<p>PicoDet-L_layout_3clsPicoDet-L_layout_17clsRT-DETR-H_layout_3clsRT-DETR-H_layout_17cls</p>
-<p><br/><br/><br/></p></details></td>
+    <td>PicoDet-S_layout_3cls<br/>PicoDet-S_layout_17cls<details>
+    <summary><b>more</b></summary>PicoDet-L_layout_3cls<br/>PicoDet-L_layout_17cls<br/>RT-DETR-H_layout_3cls<br/>RT-DETR-H_layout_17cls</details></td>
   </tr>
 
   <tr>

diff --git a/docs/pipeline_usage/pipeline_develop_guide.en.md b/docs/pipeline_usage/pipeline_develop_guide.en.md
@@ -133,7 +133,7 @@ python main.py -c paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml \
     -o Global.mode=train \
     -o Global.dataset_dir=your/dataset_dir
 ```
-In addition, PaddleX provides detailed tutorials for preparing private datasets for model fine-tuning, single-model inference, and more. For details, please refer to the [PaddleX Modules Tutorials](../../README.en.md#-documentation)
+In addition, PaddleX provides detailed tutorials for preparing private datasets for model fine-tuning, single-model inference, and more. For details, please refer to the [PaddleX Modules Tutorials](https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/ocr_modules/text_detection.html)
 
 ## 5. Pipeline Testing (Optional)
 

diff --git a/docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.en.md b/docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.en.md
@@ -757,7 +757,7 @@ You can choose the appropriate deployment method for your model pipeline based o
 If the default model weights provided by the general image multi-label classification pipeline do not meet your requirements in terms of accuracy or speed in your specific scenario, you can try to further fine-tune the existing model using <b>your own domain-specific or application-specific data</b> to improve the recognition performance of the general image multi-label classification pipeline in your scenario.
 
 ### 4.1 Model Fine-tuning
-Since the general image multi-label classification pipeline includes an image multi-label classification module, if the performance of the pipeline does not meet expectations, you need to refer to the [Customization](../../../module_usage/tutorials/cv_modules/ml_classification.en.md#Customization) section in the [Image Multi-Label Classification Module Development Tutorial](../../../module_usage/tutorials/cv_modules/ml_classification.en.md) to fine-tune the image multi-label classification model using your private dataset.
+Since the general image multi-label classification pipeline includes an image multi-label classification module, if the performance of the pipeline does not meet expectations, you need to refer to the [Customization](../../../module_usage/tutorials/cv_modules/image_multilabel_classification.en.md#Customization) section in the [Image Multi-Label Classification Module Development Tutorial](../../../module_usage/tutorials/cv_modules/image_multilabel_classification.en.md) to fine-tune the image multi-label classification model using your private dataset.
 
 ### 4.2 Model Application
 After you have completed fine-tuning training using your private dataset, you will obtain local model weights files.

diff --git a/docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md b/docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md
@@ -780,7 +780,7 @@ print_r($result[&quot;categories&quot;]);
 如果通用图像多标签分类产线提供的默认模型权重在您的场景中，精度或速度不满意，您可以尝试利用<b>您自己拥有的特定领域或应用场景的数据</b>对现有模型进行进一步的<b>微调</b>，以提升通用图像多标签分类产线的在您的场景中的识别效果。
 
 ### 4.1 模型微调
-由于通用图像多标签分类产线包含图像多标签分类模块，如果模型产线的效果不及预期，那么您需要参考[图像多标签分类模块开发教程](../../../module_usage/tutorials/cv_modules/ml_classification.md)中的[二次开发](../../../module_usage/tutorials/cv_modules/ml_classification.md#四二次开发)章节，使用您的私有数据集对图像多标签分类模型进行微调。
+由于通用图像多标签分类产线包含图像多标签分类模块，如果模型产线的效果不及预期，那么您需要参考[图像多标签分类模块开发教程](../../../module_usage/tutorials/cv_modules/image_multilabel_classification.md)中的[二次开发](../../../module_usage/tutorials/cv_modules/image_multilabel_classification.md#四二次开发)章节，使用您的私有数据集对图像多标签分类模型进行微调。
 
 ### 4.2 模型应用
 当您使用私有数据集完成微调训练后，可获得本地模型权重文件。