LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR
•
62
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
Running
on
Zero
6
LightOnOCR 1B Demo Zero
💬
Extract text from images and PDFs
Running
38
LightOnOCR 1B Demo
💬
Extract text from images and PDFs
Running
MCP
10
MCPyLate
🐕
MCP server to perform search using PyLate
Running
on
Zero
10
Vision Pipeline
🌍
Generate answers from images and text queries
Running
README
🚀