ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
Paper
•
2405.15738
•
Published
•
43
ConvLLaVA
A collection of ConvLLaVA models.
-
-
ConvLLaVA/ConvLLaVA-sft-768
Text Generation • Updated • 38 • 1 -
ConvLLaVA/ConvLLaVA-sft-1024
Text Generation • Updated • 20 -
ConvLLaVA/ConvLLaVA-sft-1536
Text Generation • Updated • 29 -
ConvLLaVA/ConvLLaVA-pretrain-768
Text Generation • Updated • 22 • 1 -
ConvLLaVA/ConvLLaVA-pretrain-1024
Text Generation • Updated • 22 -
ConvLLaVA/ConvLLaVA-pretrain-1536
Text Generation • Updated • 123 • 2 -
ConvLLaVA/ConvLLaVA-ConvNeXt-768
Updated • 28 -
ConvLLaVA/ConvLLaVA-ConvNeXt-1024
Updated • 16 -
ConvLLaVA/ConvLLaVA-ConvNeXt-1536
Updated • 1.6k • 1