vision-encoder/backbone/config.json

{
  "architectures": [
    "DINOv3ViTModel"
  ],
  "attention_dropout": 0.0,
  "drop_path_rate": 0.0,
  "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,
  "patch_size": 16,
  "pos_embed_jitter": null,
  "pos_embed_rescale": 2.0,
  "pos_embed_shift": null,
  "proj_bias": true,
  "query_bias": true,
  "rope_theta": 100.0,
  "torch_dtype": "float32",
  "transformers_version": "4.56.0.dev0",
  "use_gated_mlp": false,
  "value_bias": true
}