{   
    "model_type": "slanext", 
    "vision_config":{
        "image_size": 512,
        "output_channels":256,
        "num_channels":3,
        "patch_size":16,
        "hidden_act":"gelu",
        "layer_norm_eps":1e-6,
        "attention_dropout":0.0,
        "qkv_bias":true,
        "use_abs_pos":true,
        "use_rel_pos":true,
        "window_size":14,
        "hidden_size": 768,
        "num_hidden_layers": 12,
        "num_attention_heads": 12,
        "global_attn_indexes": [2, 5, 8, 11],
        "mlp_dim": 3072
    },
    "post_conv_in_channels": 256,
    "post_conv_out_channels": 512,
    "out_channels": 50,
    "hidden_size": 512,
    "max_text_length": 500,
    "loc_reg_num": 8
}