Model card for eva02 tiny patch14 224.mim in22k An EVA02 feature / representation model. Pretrained on ImageNet 22k with masked image modeling (using EVA CLIP as a MIM teacher) by paper authors. EVA 02 models are vision transformers with mean pooling, SwiGLU, Rotary Position Embeddings (ROPE), and extra LN in MLP (for Base & Large). NOTE: timm checkpoints are float32 for consistency with other models. Original checkpoints are float16 or bfloat16 in some cases, see originals if that's preferred. Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 5.5 GMACs: 1.7 Activations (M): 9.1 Image size: 224 x 224 Papers: EVA 02: A Visual Representation for Neon Genesis: https://arxiv.org/abs/2303.11331 EVA CLIP: Improved Training Techniques for CLIP at Scale: https://arxiv.org/abs/2303.15389 Original: https://github.com/baaivision/EVA https://huggingface.co/Yuxin CV/EVA 02 Pretrain Dataset: ImageNet 22k Model Usage Image Classification Image Embeddings Model Comparison Explore the dataset and runtime metrics of this model in timm model results. model top1 top5 param count img size eva02 large patch14 448.mim m38m ft in22k in1k 90.054 99.042 305.08 448 ev…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy