config.json

{
  "architectures": [
    "Aimv2VisionModel"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_aimv2.AIMv2Config",
    "AutoModel": "modeling_aimv2.AIMv2Model",
    "FlaxAutoModel": "modeling_flax_aimv2.FlaxAIMv2Model"
  },
  "hidden_act": "silu",
  "hidden_size": 1024,
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 2816,
  "is_native": true,
  "mlp_bias": false,
  "model_type": "aimv2_vision_model",
  "num_attention_heads": 8,
  "num_channels": 3,
  "num_hidden_layers": 24,
  "num_queries": 256,
  "patch_size": 14,
  "projection_dropout": 0.0,
  "qkv_bias": false,
  "rms_norm_eps": 1e-05,
  "torch_dtype": "float32",
  "transformers_version": "4.54.0.dev0",
  "use_bias": false,
  "use_head": false
}