← 开发者
在 GitHub 打开 
#1208
Vik Paruchuri
@VikParuchuri · USA
17.1k
加权贡献
1.95k
贡献次数
16
项目数
主要项目
- datalab-to/marker
- datalab-to/surya
- VikParuchuri/zero_to_gpt
- dataquestio/project-walkthroughs
- datalab-to/chandra
- VikParuchuri/textbook_quality
- datalab-to/lift
- VikParuchuri/texify
- VikParuchuri/tabled
- allenai/olmocr
上榜的 AI 项目9
57754
datalab-to/marker
+21
Convert PDF to markdown + JSON quickly with high accuracy
40.4k· Python· AI Engineering
35931648
datalab-to/surya
+1
OCR, layout analysis, reading order, table recognition in 90+ languages
21.5k· Python· Models
61674600
datalab-to/chandra
+0
OCR model that handles complex tables, forms, handwriting with full layout.
12.5k· Python· Applications
101227876
VikParuchuri/zero_to_gpt
+0
Go from no deep learning knowledge to implementing GPT.
1.31k· Jupyter Notebook· Tutorials
3247237
datalab-to/lift
+2
Extract structured data from documents quickly and accurately.
1.18k· Python· Models
50985501
VikParuchuri/texify
+1
Math OCR model that outputs LaTeX and markdown
1.12k· Python· AI Engineering
10923302
dataquestio/project-walkthroughs
+0
Data science, machine learning, and web development project code for https://www.youtube.com/c/Dataquestio .
1.12k· Jupyter Notebook· Tutorials
13825550
VikParuchuri/tabled
+0
Detect and extract tables to markdown and csv
745· Python· AI Engineering
17775756
VikParuchuri/textbook_quality
+0
Generate textbook-quality synthetic LLM pretraining data
507· Python· Model Development