Multimodal Autoregressive Pre-training of Large Vision Encoders
Paper
• 2411.14402 • Published
• 47
Model card for aimv2_large_patch14_336.apple_pt_dist
timm compatible AIM-v2 (https://huggingface.co/papers/2411.14402) image encoder weights from https://huggingface.co/apple/aimv2-large-patch14-336-distilled
- Downloads last month
- 47
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support