Models specialized in extracting structured information (JSON) from text, PDFs, scans, spreadsheets, etc.
AI & ML interests
Interactive NLP development
Recent Activity
View all activity
Organization Card
We are a startup building the NuExtract Platform.
We also develop open-source Information Extraction foundation models that we share here. They are often SOTA in their category, and always under MIT license; use them without restrictions 🙂.
models
36
numind/NuMarkdown-8B-Thinking-mlx-4bits
Image-to-Text
•
Updated
•
25
•
1
numind/NuMarkdown-8B-Thinking-mlx-8bits
Image-to-Text
•
Updated
•
33
•
1
numind/NuMarkdown-8B-Thinking
Image-to-Text
•
8B
•
Updated
•
3.12k
•
216
numind/NuExtract-2.0-8B
Image-Text-to-Text
•
8B
•
Updated
•
3.49k
•
46
numind/NuExtract-2.0-4B
Image-Text-to-Text
•
4B
•
Updated
•
3.81k
•
21
numind/NuExtract-2.0-2B
Image-Text-to-Text
•
2B
•
Updated
•
6.42k
•
32
numind/NuMarkdown-8B-Thinking-GGUF
8B
•
Updated
•
675
•
1
numind/NuExtract-2.0-8B-GGUF
Image-Text-to-Text
•
8B
•
Updated
•
625
•
2
numind/NuExtract-2.0-4B-GGUF
Image-Text-to-Text
•
3B
•
Updated
•
571
•
2
numind/NuExtract-2.0-2B-GGUF
Image-Text-to-Text
•
2B
•
Updated
•
337