diff --git a/demo/batch_demo.py b/demo/batch_demo.py
index 3e181f19..7f3cf468 100644
--- a/demo/batch_demo.py
+++ b/demo/batch_demo.py
@@ -1,38 +1,23 @@
 import os
-import shutil
-import tempfile
 from pathlib import Path
-
-import click
-import fitz
-from loguru import logger
-
-import magic_pdf.model as model_config
 from magic_pdf.data.batch_build_dataset import batch_build_dataset
-from magic_pdf.data.data_reader_writer import FileBasedDataReader
-from magic_pdf.data.dataset import Dataset
-from magic_pdf.libs.version import __version__
-from magic_pdf.tools.common import batch_do_parse, do_parse, parse_pdf_methods
-from magic_pdf.utils.office_to_pdf import convert_file_to_pdf
+from magic_pdf.tools.common import batch_do_parse
 
 
 def batch(pdf_dir, output_dir, method, lang):
-    model_config.__use_inside_model__ = True
-    model_config.__model_mode__ = 'full'
     os.makedirs(output_dir, exist_ok=True)
-
     doc_paths = []
     for doc_path in Path(pdf_dir).glob('*'):
         if doc_path.suffix == '.pdf':
             doc_paths.append(doc_path)
 
     # build dataset with 2 workers
-    datasets = batch_build_dataset(doc_paths, 2, lang)
+    datasets = batch_build_dataset(doc_paths, 4, lang)
 
-    os.environ["MINERU_MIN_BATCH_INFERENCE_SIZE"] = "10" # every 10 pages will be parsed in one batch
-    batch_do_parse(output_dir, [str(doc_path.stem) for doc_path in doc_paths], datasets, method, True)
+    # os.environ["MINERU_MIN_BATCH_INFERENCE_SIZE"] = "200"  # every 200 pages will be parsed in one batch
+    batch_do_parse(output_dir, [str(doc_path.stem) for doc_path in doc_paths], datasets, method)
 
 
 if __name__ == '__main__':
-    batch("batch_data", "output", "ocr", "en")
+    batch("pdfs", "output", "auto", "")
 
diff --git a/demo/demo.py b/demo/demo.py
index 2706d7d6..2a1377b6 100644
--- a/demo/demo.py
+++ b/demo/demo.py
@@ -7,18 +7,17 @@ from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
 from magic_pdf.config.enums import SupportedPdfParseMethod
 
 # args
-pdf_file_name = "demo1.pdf"  # replace with the real pdf path
-name_without_suff = pdf_file_name.split(".")[0]
+__dir__ = os.path.dirname(os.path.abspath(__file__))
+pdf_file_name = os.path.join(__dir__, "pdfs", "demo1.pdf")  # replace with the real pdf path
+name_without_extension = os.path.basename(pdf_file_name).split('.')[0]
 
 # prepare env
-local_image_dir, local_md_dir = "output/images", "output"
+local_image_dir = os.path.join(__dir__, "output", name_without_extension, "images")
+local_md_dir = os.path.join(__dir__, "output", name_without_extension)
 image_dir = str(os.path.basename(local_image_dir))
-
 os.makedirs(local_image_dir, exist_ok=True)
 
-image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(
-    local_md_dir
-)
+image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
 
 # read bytes
 reader1 = FileBasedDataReader("")
@@ -41,32 +40,29 @@ else:
     ## pipeline
     pipe_result = infer_result.pipe_txt_mode(image_writer)
 
-### draw model result on each page
-infer_result.draw_model(os.path.join(local_md_dir, f"{name_without_suff}_model.pdf"))
-
 ### get model inference result
 model_inference_result = infer_result.get_infer_res()
 
 ### draw layout result on each page
-pipe_result.draw_layout(os.path.join(local_md_dir, f"{name_without_suff}_layout.pdf"))
+pipe_result.draw_layout(os.path.join(local_md_dir, f"{name_without_extension}_layout.pdf"))
 
 ### draw spans result on each page
-pipe_result.draw_span(os.path.join(local_md_dir, f"{name_without_suff}_spans.pdf"))
+pipe_result.draw_span(os.path.join(local_md_dir, f"{name_without_extension}_spans.pdf"))
 
 ### get markdown content
 md_content = pipe_result.get_markdown(image_dir)
 
 ### dump markdown
-pipe_result.dump_md(md_writer, f"{name_without_suff}.md", image_dir)
+pipe_result.dump_md(md_writer, f"{name_without_extension}.md", image_dir)
 
 ### get content list content
 content_list_content = pipe_result.get_content_list(image_dir)
 
 ### dump content list
-pipe_result.dump_content_list(md_writer, f"{name_without_suff}_content_list.json", image_dir)
+pipe_result.dump_content_list(md_writer, f"{name_without_extension}_content_list.json", image_dir)
 
 ### get middle json
 middle_json_content = pipe_result.get_middle_json()
 
 ### dump middle json
-pipe_result.dump_middle_json(md_writer, f'{name_without_suff}_middle.json')
+pipe_result.dump_middle_json(md_writer, f'{name_without_extension}_middle.json')
diff --git a/demo/demo1.pdf b/demo/demo1.pdf
deleted file mode 100644
index c9405d62..00000000
Binary files a/demo/demo1.pdf and /dev/null differ
diff --git a/demo/demo2.pdf b/demo/demo2.pdf
deleted file mode 100644
index af924bf5..00000000
Binary files a/demo/demo2.pdf and /dev/null differ
diff --git a/demo/batch_data/demo1.pdf b/demo/pdfs/demo1.pdf
similarity index 100%
rename from demo/batch_data/demo1.pdf
rename to demo/pdfs/demo1.pdf
diff --git a/demo/batch_data/demo2.pdf b/demo/pdfs/demo2.pdf
similarity index 100%
rename from demo/batch_data/demo2.pdf
rename to demo/pdfs/demo2.pdf
diff --git a/demo/pdfs/demo3.pdf b/demo/pdfs/demo3.pdf
new file mode 100644
index 00000000..75f4e047
Binary files /dev/null and b/demo/pdfs/demo3.pdf differ
diff --git a/demo/small_ocr.pdf b/demo/pdfs/small_ocr.pdf
similarity index 100%
rename from demo/small_ocr.pdf
rename to demo/pdfs/small_ocr.pdf
diff --git a/docs/README_Ubuntu_CUDA_Acceleration_en_US.md b/docs/README_Ubuntu_CUDA_Acceleration_en_US.md
index b90ef6f2..bb500dde 100644
--- a/docs/README_Ubuntu_CUDA_Acceleration_en_US.md
+++ b/docs/README_Ubuntu_CUDA_Acceleration_en_US.md
@@ -92,7 +92,7 @@ You can find the `magic-pdf.json` file in your user directory.
 Download a sample file from the repository and test it.
 
 ```sh
-wget https://github.com/opendatalab/MinerU/raw/master/demo/small_ocr.pdf
+wget https://github.com/opendatalab/MinerU/raw/master/demo/pdfs/small_ocr.pdf
 magic-pdf -p small_ocr.pdf -o ./output
 ```
 
diff --git a/docs/README_Ubuntu_CUDA_Acceleration_zh_CN.md b/docs/README_Ubuntu_CUDA_Acceleration_zh_CN.md
index 9d22d52c..cae6b50a 100644
--- a/docs/README_Ubuntu_CUDA_Acceleration_zh_CN.md
+++ b/docs/README_Ubuntu_CUDA_Acceleration_zh_CN.md
@@ -91,7 +91,7 @@ pip install -U magic-pdf[full] -i https://mirrors.aliyun.com/pypi/simple
 从仓库中下载样本文件，并测试
 
 ```bash
-wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/demo/small_ocr.pdf
+wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/demo/pdfs/small_ocr.pdf
 magic-pdf -p small_ocr.pdf -o ./output
 ```
 
diff --git a/docs/README_Windows_CUDA_Acceleration_en_US.md b/docs/README_Windows_CUDA_Acceleration_en_US.md
index 811f73c0..539140e7 100644
--- a/docs/README_Windows_CUDA_Acceleration_en_US.md
+++ b/docs/README_Windows_CUDA_Acceleration_en_US.md
@@ -53,7 +53,7 @@ You can find the `magic-pdf.json` file in your 【user directory】 .
 Download a sample file from the repository and test it.
 
 ```powershell
-  wget https://github.com/opendatalab/MinerU/raw/master/demo/small_ocr.pdf -O small_ocr.pdf
+  wget https://github.com/opendatalab/MinerU/raw/master/demo/pdfs/small_ocr.pdf -O small_ocr.pdf
   magic-pdf -p small_ocr.pdf -o ./output
 ```
 
diff --git a/docs/README_Windows_CUDA_Acceleration_zh_CN.md b/docs/README_Windows_CUDA_Acceleration_zh_CN.md
index 73d6df70..a772e798 100644
--- a/docs/README_Windows_CUDA_Acceleration_zh_CN.md
+++ b/docs/README_Windows_CUDA_Acceleration_zh_CN.md
@@ -54,7 +54,7 @@ pip install -U magic-pdf[full] -i https://mirrors.aliyun.com/pypi/simple
 从仓库中下载样本文件，并测试
 
 ```powershell
- wget https://github.com/opendatalab/MinerU/raw/master/demo/small_ocr.pdf -O small_ocr.pdf
+ wget https://github.com/opendatalab/MinerU/raw/master/demo/pdfs/small_ocr.pdf -O small_ocr.pdf
  magic-pdf -p small_ocr.pdf -o ./output
 ```
 
diff --git a/magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/data/__init__.py b/magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/data/__init__.py
index 6cfaf436..9eef2969 100755
--- a/magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/data/__init__.py
+++ b/magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/data/__init__.py
@@ -3,21 +3,6 @@ from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
 
-import os
-import sys
-import numpy as np
-# import paddle
-import signal
-import random
-
-__dir__ = os.path.dirname(os.path.abspath(__file__))
-sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
-
-
-import copy
-# from paddle.io import Dataset, DataLoader, BatchSampler, DistributedBatchSampler
-# import paddle.distributed as dist
-
 from .imaug import transform, create_operators
 
 
diff --git a/magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/predict_system.py b/magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/predict_system.py
index 871c8fd9..e35b9a4b 100755
--- a/magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/predict_system.py
+++ b/magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/predict_system.py
@@ -16,7 +16,6 @@ class TextSystem(object):
         if self.use_angle_cls:
             self.text_classifier = predict_cls.TextClassifier(args, **kwargs)
 
-
     def get_rotate_crop_image(self, img, points):
         '''
         img_height, img_width = img.shape[0:2]
diff --git a/magic_pdf/tools/cli.py b/magic_pdf/tools/cli.py
index 94def789..27c249df 100644
--- a/magic_pdf/tools/cli.py
+++ b/magic_pdf/tools/cli.py
@@ -90,8 +90,6 @@ without method specified, auto will be used by default.""",
     default=None,
 )
 def cli(path, output_dir, method, lang, debug_able, start_page_id, end_page_id):
-    model_config.__use_inside_model__ = True
-    model_config.__model_mode__ = 'full'
     os.makedirs(output_dir, exist_ok=True)
     temp_dir = tempfile.mkdtemp()
     def read_fn(path: Path):
diff --git a/magic_pdf/tools/common.py b/magic_pdf/tools/common.py
index 8b70a21f..134c5df8 100644
--- a/magic_pdf/tools/common.py
+++ b/magic_pdf/tools/common.py
@@ -73,7 +73,7 @@ def _do_parse(
     pdf_bytes_or_dataset,
     model_list,
     parse_method,
-    debug_able,
+    debug_able=False,
     f_draw_span_bbox=True,
     f_draw_layout_bbox=True,
     f_dump_md=True,
@@ -250,7 +250,7 @@ def do_parse(
     pdf_bytes_or_dataset,
     model_list,
     parse_method,
-    debug_able,
+    debug_able=False,
     f_draw_span_bbox=True,
     f_draw_layout_bbox=True,
     f_dump_md=True,
@@ -291,7 +291,7 @@ def batch_do_parse(
     pdf_file_names: list[str],
     pdf_bytes_or_datasets: list[bytes | Dataset],
     parse_method,
-    debug_able,
+    debug_able=False,
     f_draw_span_bbox=True,
     f_draw_layout_bbox=True,
     f_dump_md=True,