{
  "architectures": [
    "LlavaNextForConditionalGeneration"
  ],
  "dtype": "bfloat16",
  "image_grid_pinpoints": [
    [
      384,
      768
    ],
    [
      768,
      384
    ],
    [
      768,
      768
    ],
    [
      1152,
      384
    ],
    [
      384,
      1152
    ]
  ],
  "image_seq_length": 729,
  "image_token_index": 32128,
  "model_type": "llava_next",
  "multimodal_projector_bias": true,
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "speakleash/Bielik-11B-v2.6-Instruct",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "eos_token_id": [
      32001,
      2
    ],
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 32768,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 50,
    "num_key_value_heads": 8,
    "pad_token_id": 2,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "use_cache": true,
    "vocab_size": 32129
  },
  "tie_word_embeddings": false,
  "transformers_version": "4.56.0",
  "use_cache": false,
  "use_image_newline_parameter": true,
  "vision_config": {
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "patch_size": 14
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "full"
}