ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
Paper
•
2405.15738
•
Published
•
47
ConvLLaVA
A collection of ConvLLaVA models.
-
-
ConvLLaVA/ConvLLaVA-sft-768
Text Generation • Updated • 17 • 1 -
ConvLLaVA/ConvLLaVA-sft-1024
Text Generation • Updated • 2 -
ConvLLaVA/ConvLLaVA-sft-1536
Text Generation • Updated • 9 -
ConvLLaVA/ConvLLaVA-pretrain-768
Text Generation • Updated • 4 • 1 -
ConvLLaVA/ConvLLaVA-pretrain-1024
Text Generation • Updated • 2 -
ConvLLaVA/ConvLLaVA-pretrain-1536
Text Generation • Updated • 4 • 2 -
ConvLLaVA/ConvLLaVA-ConvNeXt-768
Updated -
ConvLLaVA/ConvLLaVA-ConvNeXt-1024
Updated • 688 -
ConvLLaVA/ConvLLaVA-ConvNeXt-1536
Updated • 30 • 1