Visual Question Answering
Transformers
ONNX
Safetensors
PyTorch
PEFT
English
tinydoc_vlm
text-generation
document-understanding
ocr
vqa
vision-language-model
tinyml
siglip
lora
open-source
huggingface
multimodal
document-ai
deep-learning
form-understanding
table-extraction
receipt-ocr
invoice-processing
smollm
fine-tuning
edge-deployment
cpu-inference
low-resource
apache-2-0
small-language-model
slm
document-processing
text-recognition
structured-extraction
retired-checkpoint
| { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "SiglipImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 384, | |
| "width": 384 | |
| } | |
| } | |