name: "bert_base"
max_batch_size: 0
platform: "onnxruntime_onnx"
default_model_filename: "model.bin"

input [
    {
        name: "input_ids"
        data_type: TYPE_INT64
        dims: [-1, -1]
    },
    {
        name: "token_type_ids"
        data_type: TYPE_INT64
        dims: [-1, -1]
    },
    {
        name: "attention_mask"
        data_type: TYPE_INT64
        dims: [-1, -1]
    }
]

output [
    {
        name: "output"
        data_type: TYPE_FP32
        dims: [-1, -1, 30522]
    }
]

instance_group [
    {
      count: 1
      kind: KIND_GPU
    }
]