Self-Fulfilling (Mis)alignment: Base Models Collection Here we are, our base model checkpoints. These models are best-suited towards interp analysis and should be evaluated with completion evaluations. • 13 items • Updated 4 days ago • 1
facebook/dinov3-vits16plus-pretrain-lvd1689m Image Feature Extraction • 28.7M • Updated Aug 19, 2025 • 63.3k • 12
facebook/dinov3-convnext-base-pretrain-lvd1689m Image Feature Extraction • 87.6M • Updated Aug 19, 2025 • 45.5k • 12
facebook/dinov3-convnext-large-pretrain-lvd1689m Image Feature Extraction • 0.2B • Updated Aug 19, 2025 • 5.9k • 17
facebook/dinov3-vitl16-pretrain-sat493m Image Feature Extraction • 0.3B • Updated Aug 19, 2025 • 12.8k • 34
facebook/dinov3-convnext-tiny-pretrain-lvd1689m Image Feature Extraction • 27.8M • Updated Aug 19, 2025 • 26.5k • 32
facebook/dinov3-vith16plus-pretrain-lvd1689m Image Feature Extraction • 0.8B • Updated Aug 19, 2025 • 98.2k • 45
facebook/dinov3-vits16-pretrain-lvd1689m Image Feature Extraction • 21.6M • Updated Aug 19, 2025 • 137k • 69
facebook/dinov3-convnext-small-pretrain-lvd1689m Image Feature Extraction • 49.5M • Updated Aug 19, 2025 • 35.2k • 22
facebook/dinov3-vit7b16-pretrain-sat493m Image Feature Extraction • 7B • Updated Aug 19, 2025 • 2.02k • 33
facebook/dinov3-vitl16-pretrain-lvd1689m Image Feature Extraction • 0.3B • Updated Aug 19, 2025 • 578k • 170
facebook/dinov3-vitb16-pretrain-lvd1689m Image Feature Extraction • 85.7M • Updated Aug 19, 2025 • 654k • 105
facebook/dinov3-vit7b16-pretrain-lvd1689m Image Feature Extraction • Updated Aug 19, 2025 • 12k • 215
Running on CPU Upgrade Featured 1.24k Open ASR Leaderboard 🏆 1.24k Explore ASR model performance across languages and datasets