{
  "builder_config": {
    "apply_query_key_layer_scaling": false,
    "fp8": false,
    "head_size": 256,
    "hidden_act": "geglu",
    "hidden_size": 3072,
    "int8": false,
    "max_batch_size": 8,
    "max_input_len": 256,
    "max_output_len": 256,
    "max_position_embeddings": 8192,
    "max_prompt_embedding_table_size": 0,
    "name": "NeMo",
    "num_heads": 16,
    "num_kv_heads": 16,
    "num_layers": 28,
    "paged_kv_cache": false,
    "parallel_build": false,
    "pipeline_parallel": 1,
    "precision": "bfloat16",
    "tensor_parallel": 1,
    "tokens_per_block": 64,
    "use_parallel_embedding": false,
    "use_refit": false,
    "vocab_size": 256000,
    "world_size": 1
  },
  "plugin_config": {
    "attention_qk_half_accumulation": false,
    "bert_attention_plugin": false,
    "context_fmha_type": 1,
    "gemm_plugin": "bfloat16",
    "gpt_attention_plugin": "bfloat16",
    "identity_plugin": false,
    "layernorm_plugin": false,
    "layernorm_quantization_plugin": false,
    "lookup_plugin": false,
    "lora_plugin": false,
    "multi_block_mode": false,
    "nccl_plugin": false,
    "paged_kv_cache": false,
    "quantize_per_token_plugin": false,
    "quantize_tensor_plugin": false,
    "remove_input_padding": false,
    "rmsnorm_plugin": false,
    "rmsnorm_quantization_plugin": false,
    "smooth_quant_gemm_plugin": false,
    "tokens_per_block": 0,
    "use_context_fmha_for_generation": false,
    "use_custom_all_reduce": false,
    "use_paged_context_fmha": false,
    "weight_only_groupwise_quant_matmul_plugin": false,
    "weight_only_quant_matmul_plugin": false
  }
}