SDAR-VL-Instruct-8B / preprocessor_config.json
chengs18's picture
Upload model files: SDAR-VL-Instruct-8B
7e2c8f5 verified
{
"crop_size": null,
"data_format": "channels_first",
"default_to_square": false,
"device": null,
"do_center_crop": null,
"do_convert_rgb": true,
"do_normalize": true,
"do_pad": true,
"do_rescale": true,
"do_resize": true,
"image_grid_pinpoints": [
[
384,
384
],
[
384,
768
],
[
384,
1152
],
[
384,
1536
],
[
384,
1920
],
[
384,
2304
],
[
768,
384
],
[
768,
768
],
[
768,
1152
],
[
768,
1536
],
[
768,
1920
],
[
768,
2304
],
[
1152,
384
],
[
1152,
768
],
[
1152,
1152
],
[
1152,
1536
],
[
1152,
1920
],
[
1152,
2304
],
[
1536,
384
],
[
1536,
768
],
[
1536,
1152
],
[
1536,
1536
],
[
1536,
1920
],
[
1536,
2304
],
[
1920,
384
],
[
1920,
768
],
[
1920,
1152
],
[
1920,
1536
],
[
1920,
1920
],
[
1920,
2304
],
[
2304,
384
],
[
2304,
768
],
[
2304,
1152
],
[
2304,
1536
],
[
2304,
1920
],
[
2304,
2304
]
],
"image_mean": [
0.5,
0.5,
0.5
],
"image_processor_type": "LlavaOnevisionImageProcessorFast",
"image_std": [
0.5,
0.5,
0.5
],
"input_data_format": null,
"processor_class": "LlavaOnevisionProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"return_tensors": null,
"size": {
"height": 384,
"width": 384
}
}