{
  "architectures": [
    "OneVisionEncoderModel"
  ],
  "attention_dropout": 0.0,
  "dtype": "bfloat16",
  "hidden_act": "gelu",
  "hidden_size": 1024,
  "image_size": 448,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_norm_eps": 1e-06,
  "layer_norm_type": "layer_norm",
  "model_type": "onevision_encoder",
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_hidden_layers": 24,
  "patch_size": 14,
  "rope_theta": 10000.0,
  "rope_temporal_size": 64,
  "transformers_version": "4.57.1",
  "use_head": true,
  "auto_map": {
    "AutoConfig": "configuration_onevision_encoder.OneVisionEncoderConfig",
    "AutoModel": "modeling_onevision_encoder.OneVisionEncoderModel"
  }
}