| { | |
| "apply_layernorm": true, | |
| "architectures": [ | |
| "DINOv3ViTModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "drop_path_rate": 0.0, | |
| "dtype": "float32", | |
| "hidden_act": "gelu", | |
| "hidden_size": 1024, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "key_bias": false, | |
| "layer_norm_eps": 1e-05, | |
| "layerscale_value": 1.0, | |
| "mlp_bias": true, | |
| "model_type": "dinov3_vit", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "num_register_tokens": 4, | |
| "out_features": [ | |
| "stage24" | |
| ], | |
| "out_indices": [ | |
| 24 | |
| ], | |
| "patch_size": 16, | |
| "pos_embed_jitter": null, | |
| "pos_embed_rescale": 2.0, | |
| "pos_embed_shift": null, | |
| "proj_bias": true, | |
| "query_bias": true, | |
| "reshape_hidden_states": true, | |
| "rope_theta": 100.0, | |
| "stage_names": [ | |
| "stem", | |
| "stage1", | |
| "stage2", | |
| "stage3", | |
| "stage4", | |
| "stage5", | |
| "stage6", | |
| "stage7", | |
| "stage8", | |
| "stage9", | |
| "stage10", | |
| "stage11", | |
| "stage12", | |
| "stage13", | |
| "stage14", | |
| "stage15", | |
| "stage16", | |
| "stage17", | |
| "stage18", | |
| "stage19", | |
| "stage20", | |
| "stage21", | |
| "stage22", | |
| "stage23", | |
| "stage24" | |
| ], | |
| "transformers_version": "5.12.1", | |
| "use_gated_mlp": false, | |
| "value_bias": true | |
| } | |