MLLM-CL

/

MRLoRA_Router

like 0

Follow

Continual Learning of Multimodal Large Language Models 12

This PR updates the model card's pipeline_tag from visual-question-answering to image-text-to-text. This change provides a more general classification for the model, aligning with its capabilities as a Multimodal Large Language Model capable of various vision-language understanding and text generation tasks.