Models specialized in extracting structured information (JSON) from text, PDFs, scans, spreadsheets, etc.
AI & ML interests
Interactive NLP development
Recent Activity
View all activity
The best compact Zero-Shot NER models with MIT license
-
numind/NuNER_Zero
Token Classification β’ 0.4B β’ Updated β’ 13.5k β’ 99 -
numind/NuNER_Zero-span
Token Classification β’ Updated β’ 96 β’ 17 -
numind/NuNER_Zero-4k
Token Classification β’ Updated β’ 55 β’ 19 -
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data
Paper β’ 2402.15343 β’ Published β’ 16
-
NuMarkdown 8b Thinking
π37Reasoning model specialized for OCR/Markdown generation.
-
numind/NuMarkdown-8B-Thinking
Image-to-Text β’ 8B β’ Updated β’ 164k β’ 216 -
numind/NuMarkdown-8B-Thinking-GGUF
8B β’ Updated β’ 396 β’ 1 -
numind/NuMarkdown-8B-Thinking-mlx-8bits
Image-to-Text β’ Updated β’ 19 β’ 1
The Best Eng/Multi Token Classification foundation models with MIT license
-
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data
Paper β’ 2402.15343 β’ Published β’ 16 -
numind/NuNER-v2.0
Token Classification β’ 0.1B β’ Updated β’ 5.99k β’ 40 -
numind/NuNER-v0.1
Token Classification β’ Updated β’ 6.38k β’ 63 -
numind/NuNER-multilingual-v0.1
Token Classification β’ Updated β’ 6.4k β’ 68
Models specialized in extracting structured information (JSON) from text, PDFs, scans, spreadsheets, etc.
-
NuMarkdown 8b Thinking
π37Reasoning model specialized for OCR/Markdown generation.
-
numind/NuMarkdown-8B-Thinking
Image-to-Text β’ 8B β’ Updated β’ 164k β’ 216 -
numind/NuMarkdown-8B-Thinking-GGUF
8B β’ Updated β’ 396 β’ 1 -
numind/NuMarkdown-8B-Thinking-mlx-8bits
Image-to-Text β’ Updated β’ 19 β’ 1
The best compact Zero-Shot NER models with MIT license
-
numind/NuNER_Zero
Token Classification β’ 0.4B β’ Updated β’ 13.5k β’ 99 -
numind/NuNER_Zero-span
Token Classification β’ Updated β’ 96 β’ 17 -
numind/NuNER_Zero-4k
Token Classification β’ Updated β’ 55 β’ 19 -
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data
Paper β’ 2402.15343 β’ Published β’ 16
The Best Eng/Multi Token Classification foundation models with MIT license
-
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data
Paper β’ 2402.15343 β’ Published β’ 16 -
numind/NuNER-v2.0
Token Classification β’ 0.1B β’ Updated β’ 5.99k β’ 40 -
numind/NuNER-v0.1
Token Classification β’ Updated β’ 6.38k β’ 63 -
numind/NuNER-multilingual-v0.1
Token Classification β’ Updated β’ 6.4k β’ 68