Merge branch 'master' into master

opendatalab · Nov 14, 2024 · 7510a86 · 7510a86
2 parents 3f24891 + d0558ab
commit 7510a86
Show file tree

Hide file tree

Showing 8 changed files with 30 additions and 140 deletions.
diff --git a/README_zh-CN.md b/README_zh-CN.md
@@ -429,6 +429,7 @@ TODO
 # Acknowledgments
 
 - [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
+- [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
 - [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
 - [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
 - [PyMuPDF](https://github.com/pymupdf/PyMuPDF)

diff --git a/docs/download_models.py b/docs/download_models.py
diff --git a/docs/download_models_hf.py b/docs/download_models_hf.py
diff --git a/docs/how_to_download_models_en.md b/docs/how_to_download_models_en.md
@@ -8,7 +8,7 @@ Model downloads are divided into initial downloads and updates to the model dire
 Use a Python Script to Download Model Files from Hugging Face
 ```bash
 pip install huggingface_hub
-wget https://github.com/opendatalab/MinerU/raw/master/docs/download_models_hf.py -O download_models_hf.py
+wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py
 python download_models_hf.py
 ```
 The Python script will automatically download the model files and configure the model directory in the configuration file.

diff --git a/docs/how_to_download_models_zh_cn.md b/docs/how_to_download_models_zh_cn.md
@@ -8,7 +8,7 @@
   <summary>方法一：从 Hugging Face 下载模型</summary>
   <p>使用python脚本 从Hugging Face下载模型文件</p>
   <pre><code>pip install huggingface_hub
-wget https://gitee.com/myhloli/MinerU/raw/master/docs/download_models_hf.py -O download_models_hf.py
+wget https://gitee.com/myhloli/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py
 python download_models_hf.py</code></pre>
   <p>python脚本会自动下载模型文件并配置好配置文件中的模型目录</p>
 </details>
@@ -19,7 +19,7 @@ python download_models_hf.py</code></pre>
 
 ```bash
 pip install modelscope
-wget https://gitee.com/myhloli/MinerU/raw/master/docs/download_models.py -O download_models.py
+wget https://gitee.com/myhloli/MinerU/raw/master/scripts/download_models.py -O download_models.py
 python download_models.py
 ```
 python脚本会自动下载模型文件并配置好配置文件中的模型目录

diff --git a/scripts/download_models.py b/scripts/download_models.py
@@ -45,7 +45,7 @@ def download_and_modify_json(url, local_filename, modifications):
     print(f'model_dir is: {model_dir}')
     print(f'layoutreader_model_dir is: {layoutreader_model_dir}')
 
-    json_url = 'https://gitee.com/myhloli/MinerU/raw/dev/magic-pdf.template.json'
+    json_url = 'https://gitee.com/myhloli/MinerU/raw/master/magic-pdf.template.json'
     config_file_name = 'magic-pdf.json'
     home_dir = os.path.expanduser('~')
     config_file = os.path.join(home_dir, config_file_name)

diff --git a/scripts/download_models_hf.py b/scripts/download_models_hf.py
@@ -52,7 +52,7 @@ def download_and_modify_json(url, local_filename, modifications):
     print(f'model_dir is: {model_dir}')
     print(f'layoutreader_model_dir is: {layoutreader_model_dir}')
 
-    json_url = 'https://github.com/opendatalab/MinerU/raw/dev/magic-pdf.template.json'
+    json_url = 'https://github.com/opendatalab/MinerU/raw/master/magic-pdf.template.json'
     config_file_name = 'magic-pdf.json'
     home_dir = os.path.expanduser('~')
     config_file = os.path.join(home_dir, config_file_name)

diff --git a/signatures/version1/cla.json b/signatures/version1/cla.json
@@ -71,6 +71,30 @@
       "created_at": "2024-10-26T17:39:26Z",
       "repoId": 765083837,
       "pullRequestNo": 793
+    },
+    {
+      "name": "hyastar",
+      "id": 117415976,
+      "comment_id": 2466539016,
+      "created_at": "2024-11-10T01:32:42Z",
+      "repoId": 765083837,
+      "pullRequestNo": 916
+    },
+    {
+      "name": "kimi360",
+      "id": 3158007,
+      "comment_id": 2472266659,
+      "created_at": "2024-11-13T02:57:34Z",
+      "repoId": 765083837,
+      "pullRequestNo": 938
+    },
+    {
+      "name": "ProseGuys",
+      "id": 45124798,
+      "comment_id": 2472990455,
+      "created_at": "2024-11-13T09:37:42Z",
+      "repoId": 765083837,
+      "pullRequestNo": 945
     }
   ]
 }