Models from our paper "LLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language Models". https://arxiv.org/abs/2605.10641
-
CERTH-ITI-IDT/tiny-llava-Qwen2.5-7B-siglip-so400m-patch14-384
Updated • 22 -
CERTH-ITI-IDT/kd-llava-Qwen2.5-1.5B-siglip-so400m-patch14-384-3b_1_5b
2B • Updated • 1 -
CERTH-ITI-IDT/kd-llava-Qwen2.5-1.5B-siglip-so400m-patch14-384-7b_1_5b
2B • Updated • 2 -
CERTH-ITI-IDT/kd-llava-Qwen2.5-0.5B-siglip-so400m-patch14-384-3b_05b
Updated