alexshengzhili
/

llava-7bv0-mm-projector-ft-with-ocr-caption-prompted-paragraph

Text Generation

Inference Endpoints

Model card Files Files and versions Community

llava-7bv0-mm-projector-ft-with-ocr-caption-prompted-paragraph / README.md

alexshengzhili's picture

Update README.md

430d7ff over 1 year ago

|

history blame contribute delete

171 Bytes

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