{
    "architecture": "MistralForCausalLM",
    "dtype": "float16",
    "logits_dtype": "float32",
    "vocab_size": 32000,
    "max_position_embeddings": 32768,
    "hidden_size": 4096,
    "num_hidden_layers": 32,
    "num_attention_heads": 32,
    "num_key_value_heads": 8,
    "head_size": 128,
    "hidden_act": "silu",
    "intermediate_size": 14336,
    "norm_epsilon": 1e-05,
    "position_embedding_type": "rope_gpt_neox",
    "use_parallel_embedding": false,
    "embedding_sharding_dim": 0,
    "share_embedding_table": false,
    "mapping": {
        "world_size": 2,
        "tp_size": 2,
        "pp_size": 1
    },
    "quantization": {
        "quant_algo": null,
        "kv_cache_quant_algo": null,
        "group_size": 128,
        "smoothquant_val": null,
        "has_zero_point": false,
        "pre_quant_scale": false,
        "exclude_modules": [
            "lm_head"
        ]
    },
    "kv_dtype": "float16",
    "rotary_scaling": null,
    "moe_normalization_mode": null,
    "rotary_base": 1000000.0,
    "moe_num_experts": 0,
    "moe_top_k": 0,
    "moe_tp_mode": 2,
    "attn_bias": false,
    "disable_weight_only_quant_plugin": false,
    "mlp_bias": false
}