{
  "library_name": "kerasformers",
  "kerasformers_version": "1.1.3",
  "model_module": "kerasformers.models.sam3",
  "model_class": "SAM3Model",
  "variant": "sam3_saco",
  "weights": "model.weights.h5",
  "model_type": "sam3",
  "vit_hidden_size": 1024,
  "vit_intermediate_size": 4736,
  "vit_num_hidden_layers": 32,
  "vit_num_attention_heads": 16,
  "vit_image_size": 1008,
  "vit_patch_size": 14,
  "vit_window_size": 24,
  "vit_global_attn_indexes": [
    7,
    15,
    23,
    31
  ],
  "vit_rope_theta": 10000.0,
  "vit_pretrain_image_size": 336,
  "fpn_hidden_size": 256,
  "fpn_scale_factors": [
    4.0,
    2.0,
    1.0,
    0.5
  ],
  "detr_encoder_hidden_size": 256,
  "detr_encoder_num_layers": 6,
  "detr_encoder_num_attention_heads": 8,
  "detr_encoder_intermediate_size": 2048,
  "detr_encoder_dropout": 0.1,
  "detr_decoder_hidden_size": 256,
  "detr_decoder_num_layers": 6,
  "detr_decoder_num_queries": 200,
  "detr_decoder_num_attention_heads": 8,
  "detr_decoder_intermediate_size": 2048,
  "detr_decoder_dropout": 0.1,
  "mask_decoder_hidden_size": 256,
  "mask_decoder_num_upsampling_stages": 3,
  "mask_decoder_num_attention_heads": 8,
  "text_hidden_size": 1024,
  "text_projection_dim": 512,
  "image_size": 1008
}