Image-Text-to-Text
Transformers
ONNX
Safetensors
English
idefics3
image-to-text
conversational

How t to train object detection using SomlVLM-256M?

#33
by huishang2025 - opened

Hi, thanks for your great work. I am a developor of object detection.
Can this model use object detection data [x1, y1,x2,y2]? If so, what format should the training data be processed into?

Sign up or log in to comment