{
    "_attn_implementation": "eager",
    "architectures": [
        "Ernie4_5_MoeForCausalLM"
    ],
    "attention_probs_dropout_prob": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_ernie4_5_moe.Ernie4_5_MoeConfig",
        "AutoModel": "modeling_ernie4_5_moe.Ernie4_5_Model",
        "AutoModelForCausalLM": "modeling_ernie4_5_moe.Ernie4_5_MoeForCausalLM"
    },
    "bos_token_id": 1,
    "enable_mtp_magic_send": false,
    "eos_token_id": 2,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 1024,
    "ignored_index": -100,
    "initializer_range": 0.018041293779826325,
    "intermediate_size": 3072,
    "max_position_embeddings": 131072,
    "model_type": "ernie4_5_moe",
    "moe_capacity": [],
    "moe_dense_experts_token_type_id": 3,
    "moe_gate": "topk",
    "moe_gate_act": "softmax",
    "moe_group_experts": false,
    "moe_intermediate_size": 0,
    "moe_k": 2,
    "moe_layer_end_index": 17,
    "moe_layer_interval": 2,
    "moe_layer_start_index": 0,
    "moe_norm_gate_logits": true,
    "moe_num_experts": null,
    "moe_num_shared_experts": 0,
    "moe_reverse_token_drop": false,
    "moe_use_aux_free": false,
    "moe_use_hard_gate": false,
    "multi_token_pred_lambda": 0.3,
    "num_attention_heads": 16,
    "num_hidden_layers": 18,
    "num_key_value_heads": 2,
    "num_nextn_predict_layers": 0,
    "pad_token_id": 0,
    "paddleformers_version": "0.1",
    "rms_norm_eps": 1e-05,
    "rope_theta": 500000,
    "sinkhorn_2gate": true,
    "sinkhorn_temp": 0.03,
    "tensor_parallel_degree": -1,
    "tie_word_embeddings": true,
    "token_balance_loss": false,
    "token_balance_seqlen": false,
    "torch_dtype": "bfloat16",
    "use_bias": false,
    "use_cache": true,
    "use_recompute_mtp": false,
    "vocab_size": 103424,
    "weight_share_add_bias": true
}