Image-Text-to-Text
Transformers
Safetensors
English
Chinese
llava
vision-language
llm
lmm
conversational
Inference Endpoints
tiny-llava-v1-hf / preprocessor_config.json
bczhou's picture
Upload processor
33fb826 verified
raw
history blame
557 Bytes
{
"crop_size": {
"height": 336,
"width": 336
},
"do_center_crop": true,
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"feature_extractor_type": "CLIPFeatureExtractor",
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "CLIPImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"processor_class": "LlavaProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"shortest_edge": 336
}
}