{
  "_name_or_path": "tiny-random-janus",
  "aligner_config": {
    "cls": "MlpProjector",
    "model_type": "aligner",
    "params": {
      "depth": 2,
      "input_dim": 32,
      "n_embed": 32,
      "projector_type": "mlp_gelu"
    }
  },
  "architectures": [
    "MultiModalityCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_vlm.MultiModalityConfig",
    "AutoModel": "modeling_vlm.MultiModalityCausalLM",
    "AutoModelForCausalLM": "modeling_vlm.MultiModalityCausalLM"
  },
  "gen_aligner_config": {
    "cls": "MlpProjector",
    "model_type": "gen_aligner",
    "params": {
      "depth": 2,
      "input_dim": 8,
      "n_embed": 32,
      "projector_type": "mlp_gelu"
    }
  },
  "gen_head_config": {
    "cls": "vision_head",
    "model_type": "gen_head",
    "params": {
      "image_token_embed": 32,
      "image_token_size": 16384,
      "n_embed": 32
    }
  },
  "gen_vision_config": {
    "cls": "VQ-16",
    "model_type": "gen_vision",
    "params": {
      "image_token_size": 16384,
      "n_embed": 8
    }
  },
  "language_config": {
    "_attn_implementation_autoset": true,
    "head_dim": 32,
    "hidden_size": 32,
    "intermediate_size": 32,
    "max_position_embeddings": 16384,
    "model_type": "llama",
    "num_attention_heads": 1,
    "num_hidden_layers": 2,
    "num_key_value_heads": 1,
    "torch_dtype": "bfloat16",
    "vocab_size": 102400
  },
  "model_type": "multi_modality",
  "torch_dtype": "float32",
  "transformers_version": "4.47.1",
  "vision_config": {
    "cls": "CLIPVisionTower",
    "model_type": "vision",
    "params": {
      "image_size": 384,
      "model_name": "siglip_tiny_patch2_384",
      "select_feature": "same",
      "select_layer": -1
    }
  }
}