{
  "_name_or_path": "TIGER-Lab/Mantis-8B-clip-llama3",
  "architectures": [
    "GeckoForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_token_index": 128256,
  "keyword_criteria": "word",
  "model_type": "gecko",
  "pad_token_id": 128257,
  "patch_picking_strategy": "last_layer",
  "positional_information": "explicit",
  "print_keyword": false,
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "bos_token_id": 128000,
    "eos_token_id": 128001,
    "intermediate_size": 14336,
    "max_position_embeddings": 8192,
    "model_type": "llama",
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_theta": 500000.0,
    "torch_dtype": "bfloat16",
    "vocab_size": 128258
  },
  "topk": 6,
  "torch_dtype": "float16",
  "transformers_version": "4.40.2",
  "vision_config": {
    "dropout": 0.0,
    "hidden_size": 1024,
    "image_size": 336,
    "intermediate_size": 4096,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "cls",
  "visualize_patches": false,
  "visualize_topk_patches": false,
  "vocab_size": 128258
}