{
  "aligner_config": {
    "cls": "MlpProjector",
    "model_type": "aligner",
    "params": {
      "depth": 2,
      "input_dim": 1024,
      "n_embed": 4096,
      "projector_type": "mlp_gelu"
    }
  },
  "architectures": [
    "JanusProConditionalGeneration"
  ],
  "gen_aligner_config": {
    "cls": "MlpProjector",
    "model_type": "gen_aligner",
    "params": {
      "depth": 2,
      "input_dim": 8,
      "n_embed": 4096,
      "projector_type": "mlp_gelu"
    }
  },
  "gen_head_config": {
    "cls": "vision_head",
    "model_type": "gen_head",
    "params": {
      "image_token_embed": 4096,
      "image_token_size": 16384,
      "n_embed": 4096
    }
  },
  "gen_vision_config": {
    "cls": "VQ-16",
    "model_type": "gen_vision",
    "params": {
      "image_token_size": 16384,
      "n_embed": 8
    }
  },
  "num_hidden_layers": 30,
  "language_config": {
    "hidden_size": 4096,
    "intermediate_size": 11008,
    "max_position_embeddings": 16384,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 30,
    "num_key_value_heads": 32,    
    "torch_dtype": "bfloat16",
    "rms_norm_eps": 1e-6,
    "tie_word_embeddings": false,
    "vocab_size": 102400
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.33.1",
  "image_token_id": 100594,
  "vision_config": {
    "cls": "CLIPVisionTower",
    "model_type": "vision",
    "use_head": true,
    "ignore_head": true,
    "image_size": 384,
    "patch_size": 16,
    "hidden_size": 1024,
    "num_hidden_layers": 24,
    "num_attention_heads": 16,
    "intermediate_size": 4096,
    "mlp_ratio": 4,
    "global_pool": "map",
    "use_checkpoint": false,     
    "params": {
      "image_size": 384,
      "model_name": "siglip_large_patch16_384",
      "select_feature": "same",
      "select_layer": -1
    }
  }
}