tabby/testdata/tiny-70M/models/fastertransformer/config.pbtxt

name: "fastertransformer"
backend: "fastertransformer"
default_model_filename: "tiny-70M"
max_batch_size: 1024

model_transaction_policy {
  decoupled: False
}

input [
  {
    name: "input_ids"
    data_type: TYPE_UINT32
    dims: [ -1 ]
  },
  {
    name: "start_id"
    data_type: TYPE_UINT32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "end_id"
    data_type: TYPE_UINT32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "input_lengths"
    data_type: TYPE_UINT32
    dims: [ 1 ]
    reshape: { shape: [ ] }
  },
  {
    name: "request_output_len"
    data_type: TYPE_UINT32
    dims: [ -1 ]
  },
  {
    name: "runtime_top_k"
    data_type: TYPE_UINT32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "runtime_top_p"
    data_type: TYPE_FP32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "beam_search_diversity_rate"
    data_type: TYPE_FP32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "temperature"
    data_type: TYPE_FP32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "len_penalty"
    data_type: TYPE_FP32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "repetition_penalty"
    data_type: TYPE_FP32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "random_seed"
    data_type: TYPE_UINT64
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "is_return_log_probs"
    data_type: TYPE_BOOL
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "beam_width"
    data_type: TYPE_UINT32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "bad_words_list"
    data_type: TYPE_INT32
    dims: [ 2, -1 ]
    optional: true
  },
  {
    name: "stop_words_list"
    data_type: TYPE_INT32
    dims: [ 2, -1 ]
    optional: true
  },
  {
    name: "prompt_learning_task_name_ids"
    data_type: TYPE_UINT32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "top_p_decay"
    data_type: TYPE_FP32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "top_p_min"
    data_type: TYPE_FP32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  },
  {
    name: "top_p_reset_ids"
    data_type: TYPE_UINT32
    dims: [ 1 ]
    reshape: { shape: [ ] }
    optional: true
  }
]
output [
  {
    name: "output_ids"
    data_type: TYPE_UINT32
    dims: [ -1, -1 ]
  },
  {
    name: "sequence_length"
    data_type: TYPE_UINT32
    dims: [ -1 ]
  },
  {
    name: "cum_log_probs"
    data_type: TYPE_FP32
    dims: [ -1 ]
  },
  {
    name: "output_log_probs"
    data_type: TYPE_FP32
    dims: [ -1, -1 ]
  }
]
instance_group [
  {
    count: 1
    kind: KIND_CPU
  }
]
parameters {
  key: "tensor_para_size"
  value: {
    string_value: "1"
  }
}
parameters {
  key: "pipeline_para_size"
  value: {
    string_value: "1"
  }
}
parameters {
  key: "data_type"
  value: {
    string_value: "fp32"
  }
}
parameters {
  key: "model_type"
  value: {
    string_value: "GPT-NeoX"
  }
}
parameters {
  key: "model_checkpoint_path"
  value: {
    string_value: "/model/fastertransformer/1/1-gpu"
  }
}
parameters {
  key: "enable_custom_all_reduce"
  value: {
    string_value: "0"
  }
}