Image-Text-to-Text
Transformers
Safetensors
youtu_vl
text-generation
conversational
custom_code
Youtu-Parsing / preprocessor_config.json
Yinsongliu's picture
Upload model with LFS assets
c13c3aa
raw
history blame contribute delete
559 Bytes
{
"auto_map": {
"AutoProcessor": "processing_youtu_vl.YoutuVLProcessor",
"AutoImageProcessor": "image_processing_siglip2_fast.Siglip2ImageProcessorFast"
},
"processor_class": "YoutuVLProcessor",
"do_convert_rgb": null,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.5,
0.5,
0.5
],
"image_processor_type": "Siglip2ImageProcessorFast",
"image_std": [
0.5,
0.5,
0.5
],
"max_num_patches": 256,
"patch_size": 16,
"resample": 2,
"rescale_factor": 0.00392156862745098
}