config.json

{
    "architectures": [
        "LlavaOnevisionForConditionalGeneration"
    ],
    "image_grid_pinpoints": [
        [
            384,
            384
        ],
        [
            384,
            768
        ],
        [
            384,
            1152
        ],
        [
            384,
            1536
        ],
        [
            384,
            1920
        ],
        [
            384,
            2304
        ],
        [
            768,
            384
        ],
        [
            768,
            768
        ],
        [
            768,
            1152
        ],
        [
            768,
            1536
        ],
        [
            768,
            1920
        ],
        [
            768,
            2304
        ],
        [
            1152,
            384
        ],
        [
            1152,
            768
        ],
        [
            1152,
            1152
        ],
        [
            1152,
            1536
        ],
        [
            1152,
            1920
        ],
        [
            1152,
            2304
        ],
        [
            1536,
            384
        ],
        [
            1536,
            768
        ],
        [
            1536,
            1152
        ],
        [
            1536,
            1536
        ],
        [
            1536,
            1920
        ],
        [
            1536,
            2304
        ],
        [
            1920,
            384
        ],
        [
            1920,
            768
        ],
        [
            1920,
            1152
        ],
        [
            1920,
            1536
        ],
        [
            1920,
            1920
        ],
        [
            1920,
            2304
        ],
        [
            2304,
            384
        ],
        [
            2304,
            768
        ],
        [
            2304,
            1152
        ],
        [
            2304,
            1536
        ],
        [
            2304,
            1920
        ],
        [
            2304,
            2304
        ]
    ],
    "image_token_index": 7,
    "model_type": "llava_onevision",
    "projector_hidden_act": "gelu",
    "text_config": {
        "_name_or_path": "/gpfs/projects/bsc88/text/models/vision/OneVision/checkpoints/bsc/bsc_7b_hf_llama_instructed",
        "architectures": [
            "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "bos_token_id": 4,
        "eos_token_id": 5,
        "head_dim": 128,
        "intermediate_size": 11008,
        "max_position_embeddings": 8192,
        "mlp_bias": false,
        "model_type": "llama",
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "torch_dtype": "bfloat16",
        "use_cache": false,
        "vocab_size": 256000
    },
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.46.0.dev0",
    "use_image_newline_parameter": true,
    "video_token_index": 8,
    "vision_aspect_ratio": "anyres_max_9",
    "vision_config": {
        "hidden_size": 1152,
        "image_size": 384,
        "intermediate_size": 4304,
        "model_type": "siglip_vision_model",
        "num_attention_heads": 16,
        "num_hidden_layers": 26,
        "patch_size": 14,
        "vision_use_head": false
    },
    "vision_feature_layer": -1,
    "vision_feature_select_strategy": "full"
}