{ "architectures": [ "Ernie4_5_MoeForCausalLM" ], "bos_token_id": 1, "eos_token_id": 2, "dtype": "bfloat16", "hidden_act": "silu", "hidden_size": 8192, "intermediate_size": 28672, "max_position_embeddings": 131072, "model_type": "ernie4_5_moe", "num_attention_heads": 64, "num_key_value_heads": 8, "num_hidden_layers": 54, "pad_token_id": 0, "rms_norm_eps": 1e-05, "use_cache": false, "vocab_size": 103424, "rope_theta": 500000, "use_rmsnorm": true, "use_bias": false, "moe_num_experts": 64, "moe_layer_start_index": 3, "moe_intermediate_size": 3584, "moe_capacity": [ 64, 64, 64 ], "moe_gate": "topk", "moe_k": 8, "moe_layer_interval": 1, "moe_use_aux_free": true, "num_nextn_predict_layers": 1, "tie_word_embeddings": false, "quantization_config": { "dense_quant_type": "wint8", "moe_quant_type": "w4w2", "quantization": "wint2", "moe_quant_config": { "moe_w4_quant_config": { "quant_type": "wint4", "quant_granularity": "per_channel", "quant_start_layer": 0, "quant_end_layer": 6 }, "moe_w2_quant_config": { "quant_type": "wint2", "quant_granularity": "pp_acc", "quant_group_size": 64, "quant_start_layer": 7, "quant_end_layer": 53 } } } }