{
  "architectures": [
    "MiniCPMV"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "openbmb/MiniCPM-V-4--configuration_minicpm.MiniCPMVConfig",
    "AutoModel": "openbmb/MiniCPM-V-4--modeling_minicpmv.MiniCPMV",
    "AutoModelForCausalLM": "openbmb/MiniCPM-V-4--modeling_minicpmv.MiniCPMV"
  },
  "batch_vision_input": true,
  "bos_token_id": 1,
  "drop_vision_last_layer": false,
  "eos_token_id": [
    2,
    73440
  ],
  "head_dim": 32,
  "hidden_act": "silu",
  "hidden_size": 128,
  "image_size": 448,
  "initializer_range": 0.1,
  "intermediate_size": 128,
  "max_position_embeddings": 32768,
  "mlp_bias": false,
  "model_type": "minicpmv",
  "num_attention_heads": 2,
  "num_hidden_layers": 2,
  "num_key_value_heads": 1,
  "pad_token_id": 2,
  "patch_size": 14,
  "pretraining_tp": 1,
  "query_num": 64,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "factor": 1.0,
    "long_factor": [
      0.9977997200264581,
      1.014658295992452,
      1.0349680404997148,
      1.059429246056193,
      1.0888815016813513,
      1.1243301355211495,
      1.166977103606075,
      1.2182568066927284,
      1.2798772354275727,
      1.3538666751582975,
      1.4426259039919596,
      1.5489853358570191,
      1.6762658237220625,
      1.8283407612492941,
      2.0096956085876183,
      2.225478927469756
    ],
    "original_max_position_embeddings": 32786,
    "rope_type": "longrope",
    "short_factor": [
      0.9977997200264581,
      1.014658295992452,
      1.0349680404997148,
      1.059429246056193,
      1.0888815016813513,
      1.1243301355211495,
      1.166977103606075,
      1.2182568066927284,
      1.2798772354275727,
      1.3538666751582975,
      1.4426259039919596,
      1.5489853358570191,
      1.6762658237220625,
      1.8283407612492941,
      2.0096956085876183,
      2.225478927469756
    ]
  },
  "rope_theta": 10000.0,
  "slice_config": {
    "max_slice_nums": 9,
    "model_type": "minicpmv",
    "patch_size": 14,
    "scale_resolution": 448
  },
  "slice_mode": true,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.56.0.dev0",
  "use_cache": true,
  "use_image_id": true,
  "version": 4.0,
  "vision_batch_size": 16,
  "vision_config": {
    "_attn_implementation_autoset": true,
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 64,
    "image_size": 980,
    "intermediate_size": 128,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 2,
    "num_channels": 3,
    "num_hidden_layers": 2,
    "patch_size": 14
  },
  "vocab_size": 73448
}