{
  "_name_or_path": "ibm-granite/granite-vision-3.1-2b-preview",
  "architectures": [
    "LlavaNextForConditionalGeneration"
  ],
  "image_grid_pinpoints": [
    [
      384,
      768
    ],
    [
      384,
      1152
    ],
    [
      384,
      1536
    ],
    [
      384,
      1920
    ],
    [
      384,
      2304
    ],
    [
      384,
      2688
    ],
    [
      384,
      3072
    ],
    [
      384,
      3456
    ],
    [
      384,
      3840
    ],
    [
      768,
      384
    ],
    [
      768,
      768
    ],
    [
      768,
      1152
    ],
    [
      768,
      1536
    ],
    [
      768,
      1920
    ],
    [
      1152,
      384
    ],
    [
      1152,
      768
    ],
    [
      1152,
      1152
    ],
    [
      1536,
      384
    ],
    [
      1536,
      768
    ],
    [
      1920,
      384
    ],
    [
      1920,
      768
    ],
    [
      2304,
      384
    ],
    [
      2688,
      384
    ],
    [
      3072,
      384
    ],
    [
      3456,
      384
    ],
    [
      3840,
      384
    ]
  ],
  "image_seq_length": 576,
  "image_token_index": 49155,
  "model_type": "llava_next",
  "multimodal_projector_bias": true,
  "projector_hidden_act": "gelu",
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "text_config": {
    "architectures": [
      "GraniteForCausalLM"
    ],
    "attention_dropout": 0.1,
    "attention_multiplier": 0.015625,
    "bos_token_id": 0,
    "embedding_multiplier": 12.0,
    "eos_token_id": 0,
    "hidden_size": 2048,
    "intermediate_size": 8192,
    "logits_scaling": 8.0,
    "max_position_embeddings": 16384,
    "model_type": "granite",
    "num_hidden_layers": 40,
    "num_key_value_heads": 8,
    "pad_token_id": 0,
    "residual_multiplier": 0.22,
    "rms_norm_eps": 1e-05,
    "rope_theta": 300000,
    "tie_word_embeddings": true,
    "torch_dtype": "float16",
    "vocab_size": 49156
  },
  "tie_word_embeddings": true,
  "torch_dtype": "float16",
  "transformers_version": "4.50.0.dev0",
  "use_image_newline_parameter": true,
  "vision_config": {
    "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_hidden_layers": 27,
    "patch_size": 14,
    "torch_dtype": "float16"
  },
  "vision_feature_layer": [
    -24,
    -20,
    -12,
    -1
  ],
  "vision_feature_select_strategy": "full"
}