{
    "version": "0.9.0.dev2024020600",
    "pretrained_config": {
        "architecture": "PhiForCausalLM",
        "dtype": "float16",
        "logits_dtype": "float32",
        "vocab_size": 51200,
        "max_position_embeddings": 2048,
        "hidden_size": 2560,
        "num_hidden_layers": 32,
        "num_attention_heads": 32,
        "num_key_value_heads": 32,
        "head_size": 80,
        "hidden_act": "gelu_new",
        "intermediate_size": 10240,
        "norm_epsilon": 1e-05,
        "position_embedding_type": "learned_absolute",
        "use_prompt_tuning": false,
        "use_parallel_embedding": false,
        "embedding_sharding_dim": 0,
        "share_embedding_table": false,
        "mapping": {
            "world_size": 1,
            "tp_size": 1,
            "pp_size": 1
        },
        "kv_dtype": "float16",
        "max_lora_rank": 64,
        "partial_rotary_factor": 0.4,
        "rope_theta": 10000.0,
        "rotary_base": 10000.0,
        "quantization": {
            "quant_algo": null,
            "kv_cache_quant_algo": null,
            "group_size": 128,
            "has_zero_point": false,
            "pre_quant_scale": false,
            "exclude_modules": null,
            "sq_use_plugin": false
        }
    },
    "build_config": {
        "max_input_len": 1024,
        "max_output_len": 1024,
        "max_batch_size": 1,
        "max_beam_width": 1,
        "max_num_tokens": 1024,
        "max_prompt_embedding_table_size": 0,
        "gather_context_logits": false,
        "gather_generation_logits": false,
        "strongly_typed": false,
        "builder_opt": null,
        "profiling_verbosity": "layer_names_only",
        "plugin_config": {
            "bert_attention_plugin": "float16",
            "gpt_attention_plugin": "float16",
            "gemm_plugin": "float16",
            "smooth_quant_gemm_plugin": null,
            "identity_plugin": null,
            "layernorm_quantization_plugin": null,
            "rmsnorm_quantization_plugin": null,
            "nccl_plugin": null,
            "lookup_plugin": null,
            "lora_plugin": null,
            "weight_only_groupwise_quant_matmul_plugin": null,
            "weight_only_quant_matmul_plugin": null,
            "quantize_per_token_plugin": false,
            "quantize_tensor_plugin": false,
            "context_fmha": true,
            "context_fmha_fp32_acc": false,
            "paged_kv_cache": true,
            "remove_input_padding": true,
            "use_custom_all_reduce": true,
            "multi_block_mode": false,
            "enable_xqa": true,
            "attention_qk_half_accumulation": false,
            "tokens_per_block": 128,
            "use_paged_context_fmha": false,
            "use_context_fmha_for_generation": false
        }
    }
}