numind/ nuextract3:bf16

59 yesterday

NuExtract3 is a 4B vision-language reasoning model by NuMind for local document understanding. Turn text and document images into structured JSON or clean Markdown with Ollama, with support for multilingual documents, OCR, and template generation.

vision tools thinking
... /
json
d89ef49ce9cd · 1.2kB
{
"image_processor": {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.5,
0.5,
0.5
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.5,
0.5,
0.5
],
"merge_size": 2,
"patch_size": 16,
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 16777216,
"shortest_edge": 65536
},
"temporal_patch_size": 2
},
"processor_class": "Qwen3VLProcessor",
"video_processor": {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"do_sample_frames": true,
"fps": 2,
"image_mean": [
0.5,
0.5,
0.5
],
"image_std": [
0.5,
0.5,
0.5
],
"max_frames": 768,
"merge_size": 2,
"min_frames": 4,
"patch_size": 16,
"resample": 3,
"rescale_factor": 0.00392156862745098,
"return_metadata": false,
"size": {
"longest_edge": 25165824,
"shortest_edge": 4096
},
"temporal_patch_size": 2,
"video_processor_type": "Qwen3VLVideoProcessor"
}
}