Image-Text-to-Text
Transformers
Safetensors
English
internvl_chat
feature-extraction
mathematics
reasoning
multi-modal-qa
math-qa
figure-qa
geometry-qa
math-word-problem
textbook-qa
vqa
geometry-diagram
synthetic-scene
chart
plot
scientific-figure
table
function-plot
abstract-scene
puzzle-test
document-image
science
conversational
custom_code
{ | |
"crop_size": 448, | |
"do_center_crop": true, | |
"do_normalize": true, | |
"do_resize": true, | |
"feature_extractor_type": "CLIPFeatureExtractor", | |
"image_mean": [ | |
0.485, | |
0.456, | |
0.406 | |
], | |
"image_std": [ | |
0.229, | |
0.224, | |
0.225 | |
], | |
"resample": 3, | |
"size": 448 | |
} | |