{
  "architectures": [
    "LlavaNextForConditionalGeneration"
  ],
  "bos_token_id": 1,
  "dtype": "float32",
  "eos_token_id": 2,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_seq_length": 576,
  "image_token_index": 32000,
  "model_type": "llava_next",
  "multimodal_projector_bias": true,
  "pad_token_id": 32001,
  "projector_hidden_act": "gelu",
  "text_config": {
    "architectures": [
      "MistralForCausalLM"
    ],
    "attention_dropout": 0.0,
    "dtype": "float32",
    "head_dim": null,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "max_position_embeddings": 32768,
    "model_type": "mistral",
    "num_attention_heads": 32,
    "num_hidden_layers": 12,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_theta": 10000.0,
    "sliding_window": 32,
    "use_cache": true,
    "vocab_size": 32064
  },
  "tie_word_embeddings": false,
  "transformers_version": "4.57.1",
  "vision_config": {
    "attention_dropout": 0.0,
    "dropout": 0.0,
    "dtype": "float32",
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "image_size": 336,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 1,
    "patch_size": 14,
    "projection_dim": 768
  },
  "vision_feature_layer": -1,
  "vision_feature_select_strategy": "default"
}