-
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 78 -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 1.34M • 2.28k -
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 22k • 1.17k -
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text • 4B • Updated • 61.2k • 426
www.minds.com/jelyazko/
21world
AI & ML interests
[1][0] 2b is half size of 4b [3][2] [1][0] (new) sentence at once = token. PRECOMPUTED AI WEIGHTS
! INNOVATIONS ARE USED INSTEAD REFUSALS !
Known Training Algos:
- Backpropagation
- Forward Forward
- Predictive Coding
- Q-Learning ?
-....
|for correct ds1307 pinout 8-stars(0-14B models Q4)| for Diffusion LLM 9-stars | Teach llms on ASCII/Text Based STL Modeling , ic pinouts .optionaly:patents. |context editing| .exact size of all obj dimentions. Virtualization of ai/ml in mcu .Funding require.///until llms are weak///
https://github.com/sponsors/jelspace
https://ko-fi.com/21world
https://rumble.com/c/c-5865836
https://www.buymeacoffee.com/21world
Recent Activity
liked
a model
2 days ago
cturan/MiniMax-M2-GGUF
updated
a collection
2 days ago
18\ other models
updated
a collection
4 days ago
18\ other models
Organizations
-
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 78 -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 1.34M • 2.28k -
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 22k • 1.17k -
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text • 4B • Updated • 61.2k • 426
67 \ vision -> 3d printer/lathe/.../.../ control
datasets
0
None public yet