This is the feature alignment pre-training work to train only only the multi-modal projector. "Predict" paragraph given caption, ocr and image token

Downloads last month
3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Space using alexshengzhili/llava-7bv0-mm-projector-ft-with-ocr-caption-prompted-paragraph 1