Image Classification
timm
PyTorch
Safetensors
Transformers
variance_pad_eva
feature-extraction
custom_code
Instructions to use bn22/vit_medium_patch28_rope_reg4_gap_224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use bn22/vit_medium_patch28_rope_reg4_gap_224 with timm:
import timm model = timm.create_model("hf_hub:bn22/vit_medium_patch28_rope_reg4_gap_224", pretrained=True) - Transformers
How to use bn22/vit_medium_patch28_rope_reg4_gap_224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="bn22/vit_medium_patch28_rope_reg4_gap_224", trust_remote_code=True) pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bn22/vit_medium_patch28_rope_reg4_gap_224", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "VariancePadEvaModel" | |
| ], | |
| "attn_pool_num_heads": 16, | |
| "auto_map": { | |
| "AutoConfig": "variance_pad_eva.VariancePadEvaConfig", | |
| "AutoModel": "variance_pad_eva.VariancePadEvaModel" | |
| }, | |
| "class_token": false, | |
| "depth": 20, | |
| "dtype": "float32", | |
| "dynamic_img_size": true, | |
| "embed_dim": 512, | |
| "global_pool": "map", | |
| "img_size": 224, | |
| "init_values": 1e-05, | |
| "mlp_ratio": 2.6667, | |
| "model_type": "variance_pad_eva", | |
| "num_classes": 0, | |
| "num_heads": 16, | |
| "num_reg_tokens": 4, | |
| "pad_variance_threshold": 0.01, | |
| "patch_size": 28, | |
| "qkv_bias": false, | |
| "qkv_fused": true, | |
| "ref_feat_shape": [ | |
| 16, | |
| 16 | |
| ], | |
| "transformers_version": "5.0.0", | |
| "use_abs_pos_emb": false, | |
| "use_rot_pos_emb": true | |
| } | |