config.json

{
    "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
        ]
    ],
    "tie_word_embeddings": true,
    "transformers_version": "4.45.0.dev0",
    "architectures": [
        "LlavaNextForConditionalGeneration"
    ],
    "model_type": "llava_next",
    "use_image_newline_parameter": true,
    "vision_feature_layer": [
        3,
        7,
        15,
        26
    ],
    "vision_feature_select_strategy": "full",
    "text_config": {
        "architectures": [
            "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.1,
        "attention_multiplier": 0.015625,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "logits_scaling": 8.0,
        "max_position_embeddings": 16384,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 300000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.0.dev0",
        "use_cache": true,
        "vocab_size": 49156
    },
    "image_token_index": 49155,
    "vision_config": {
        "hidden_size": 1152,
        "image_size": 384,
        "intermediate_size": 4304,
        "model_type": "siglip_vision_model",
        "num_attention_heads": 16,
        "num_hidden_layers": 27,
        "patch_size": 14
    }
}