config.json

{
  "architectures": [
    "Qwen3NextForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0,
  "bos_token_id": 151643,
  "decoder_sparse_step": 1,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "full_attention_interval": 4,
  "head_dim": 256,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_key_head_dim": 128,
  "linear_num_key_heads": 16,
  "linear_num_value_heads": 32,
  "linear_value_head_dim": 128,
  "max_position_embeddings": 262144,
  "merge_args": {
    "balance_group_size": 32,
    "dataset": "c4+math+the-stack-smol",
    "expert_saliency": "reap",
    "gate_softmax": true,
    "group": "freq_logits",
    "merge": "align_logits_weights",
    "merge_size": 384,
    "merger_bs": 3072,
    "merger_seq_len": 512,
    "pca_dim": 64,
    "precompute_input": false,
    "use_gate_output": true
  },
  "mlp_only_layers": [],
  "model_type": "qwen3_next",
  "moe_intermediate_size": 512,
  "norm_topk_prob": true,
  "num_attention_heads": 16,
  "num_experts": 384,
  "num_experts_per_tok": 10,
  "num_hidden_layers": 48,
  "num_key_value_heads": 2,
  "output_router_logits": false,
  "partial_rotary_factor": 0.25,
  "quantization_config": {
    "bits": 4,
    "group_size": 32,
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true,
    "modules_to_not_convert": [
      "lm_head",
      "linear_attn",
      "self_attn",
      "shared_expert",
      "shared_expert_gate",
      "gate",
      "input_layernorm",
      "post_attention_layernorm",
      "embed_tokens",
      "norm",
      "k_norm",
      "q_norm"
    ],
    "ignore": [
      "lm_head",
      "re:.*mlp\\.gate$",
      "re:.*linear_attn\\.in_proj_a$",
      "re:.*linear_attn\\.in_proj_b$",
      "re:.*shared_expert\\..*"
    ]
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000,
  "router_aux_loss_coef": 0.001,
  "shared_expert_intermediate_size": 512,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}