{
  "architectures": [
    "Qwen3MoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "decoder_sparse_step": 1,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "max_position_embeddings": 262144,
  "max_window_layers": 48,
  "merge_args": {
    "batch_size": 8,
    "cache_dir": null,
    "dataset": "c4+math+code",
    "download": false,
    "group_size": 16,
    "grouping": "ream",
    "merge_size": 96,
    "merging": "logits+weights",
    "mix_ratio": "0.5,0.25,0.25",
    "model": "/data/models/Qwen3-30B-A3B-Instruct-2507-BF16",
    "mtp_safe_tensors": null,
    "no_gate_output": false,
    "no_gated_sim": false,
    "no_sequential": false,
    "saliency": "reap",
    "save_path": "/data/models/Qwen3-30B-Instruct-2507-REAM-BF16"
  },
  "mlp_only_layers": [],
  "model_type": "qwen3_moe",
  "moe_intermediate_size": 768,
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 48,
  "num_key_value_heads": 4,
  "num_local_experts": 96,
  "output_router_logits": false,
  "pad_token_id": null,
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true,
    "modules_to_not_convert": [],
    "ignore": [
      "lm_head"
    ]
  },
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "rope_theta": 10000000,
    "rope_type": "default"
  },
  "router_aux_loss_coef": 0.001,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.4",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}