{
  "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,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 8192,
  "ignored_index": -100,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "max_sequence_length": null,
  "model_type": "ernie4_5_moe",
  "moe_capacity": [
    64,
    64,
    64
  ],
  "moe_dropout_prob": 0.0,
  "moe_gate": "topk",
  "moe_gate_act": "softmax",
  "moe_intermediate_size": 3584,
  "moe_k": 8,
  "moe_layer_end_index": 53,
  "moe_layer_interval": 1,
  "moe_layer_start_index": 3,
  "moe_num_experts": 64,
  "moe_use_aux_free": true,
  "num_attention_heads": 64,
  "num_hidden_layers": 54,
  "num_key_value_heads": 8,
  "num_nextn_predict_layers": 1,
  "pad_token_id": 0,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 128,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.layers.1.self_attn.q_proj",
      "model.layers.1.self_attn.k_proj",
      "model.layers.1.self_attn.v_proj",
      "model.layers.1.self_attn.o_proj",
      "model.layers.1.mlp.gate_proj",
      "model.layers.1.mlp.up_proj",
      "model.layers.1.mlp.down_proj",
      "model.layers.2.self_attn.q_proj",
      "model.layers.2.self_attn.k_proj",
      "model.layers.2.self_attn.v_proj",
      "model.layers.2.self_attn.o_proj",
      "model.layers.2.mlp.gate_proj",
      "model.layers.2.mlp.up_proj",
      "model.layers.2.mlp.down_proj",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  },
  "rms_norm_eps": 1e-05,
  "rope_theta": 500000,
  "sinkhorn_2gate": true,
  "sinkhorn_temp": 0.03,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.0",
  "use_bias": false,
  "use_cache": true,
  "use_flash_attention": false,
  "use_moe": true,
  "use_rmsnorm": true,
  "use_sliding_window": null,
  "vocab_size": 103424,
  "weight_share_add_bias": true
}