config.json

{
    "mlp_bias": false,
    "attn_bias": false,
    "rotary_base": 500000.0,
    "rotary_scaling": {
        "factor": 8.0,
        "low_freq_factor": 1.0,
        "high_freq_factor": 4.0,
        "original_max_position_embeddings": 8192,
        "rope_type": "llama3"
    },
    "residual_mlp": false,
    "disable_weight_only_quant_plugin": false,
    "moe": {
        "num_experts": 0,
        "top_k": 0,
        "normalization_mode": null,
        "tp_mode": 0
    },
    "architecture": "LlamaForCausalLM",
    "dtype": "bfloat16",
    "vocab_size": 128256,
    "hidden_size": 8192,
    "num_hidden_layers": 80,
    "num_attention_heads": 64,
    "hidden_act": "silu",
    "logits_dtype": "float32",
    "norm_epsilon": 1e-05,
    "position_embedding_type": "rope_gpt_neox",
    "max_position_embeddings": 131072,
    "num_key_value_heads": 8,
    "intermediate_size": 28672,
    "mapping": {
        "world_size": 4,
        "gpus_per_node": 8,
        "tp_size": 4,
        "pp_size": 1,
        "moe_tp_size": 4,
        "moe_ep_size": 1
    },
    "quantization": {
        "quant_algo": null,
        "kv_cache_quant_algo": null,
        "group_size": 128,
        "smoothquant_val": null,
        "clamp_val": null,
        "has_zero_point": false,
        "pre_quant_scale": false,
        "exclude_modules": null
    },
    "use_parallel_embedding": false,
    "embedding_sharding_dim": 0,
    "share_embedding_table": false,
    "head_size": 128,
    "qk_layernorm": false
}