{
  "_name_or_path": "CIDAS/clipseg-rd16",
  "architectures": [
    "CLIPSegForImageSegmentation"
  ],
  "conditional_layer": 0,
  "decoder_attention_dropout": 0.0,
  "decoder_hidden_act": "quick_gelu",
  "decoder_intermediate_size": 2048,
  "decoder_num_attention_heads": 4,
  "extract_layers": [
    3,
    6,
    9
  ],
  "initializer_factor": 1.0,
  "logit_scale_init_value": 2.6592,
  "model_type": "clipseg",
  "projection_dim": 512,
  "reduce_dim": 16,
  "text_config": {
    "bos_token_id": 0,
    "dropout": 0.0,
    "eos_token_id": 2,
    "model_type": "clipseg_text_model"
  },
  "transformers_version": "4.37.0.dev0",
  "use_complex_transposed_convolution": false,
  "vision_config": {
    "dropout": 0.0,
    "model_type": "clipseg_vision_model",
    "patch_size": 16
  }
}