{ "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, "mlp_only_layers": [], "model_type": "qwen3_next", "moe_intermediate_size": 512, "norm_topk_prob": true, "num_attention_heads": 16, "num_experts": 512, "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": { "algo_config": null, "exclude": [ "model.layers.0.linear_attn.in_proj_qkvz", "model.layers.0.linear_attn.in_proj_ba", "model.layers.0.mlp.gate", "model.layers.0.mlp.shared_expert_gate", "model.layers.1.linear_attn.in_proj_qkvz", "model.layers.1.linear_attn.in_proj_ba", "model.layers.1.mlp.gate", "model.layers.1.mlp.shared_expert_gate", "model.layers.2.linear_attn.in_proj_qkvz", "model.layers.2.linear_attn.in_proj_ba", "model.layers.2.mlp.gate", "model.layers.2.mlp.shared_expert_gate", "model.layers.3.self_attn.q_proj", "model.layers.3.self_attn.k_proj", "model.layers.3.self_attn.v_proj", "model.layers.3.mlp.gate", "model.layers.3.mlp.shared_expert_gate", "model.layers.4.linear_attn.in_proj_qkvz", "model.layers.4.linear_attn.in_proj_ba", "model.layers.4.mlp.gate", "model.layers.4.mlp.shared_expert_gate", "model.layers.5.linear_attn.in_proj_qkvz", "model.layers.5.linear_attn.in_proj_ba", "model.layers.5.mlp.gate", "model.layers.5.mlp.shared_expert_gate", "model.layers.6.linear_attn.in_proj_qkvz", "model.layers.6.linear_attn.in_proj_ba", "model.layers.6.mlp.gate", "model.layers.6.mlp.shared_expert_gate", "model.layers.7.self_attn.q_proj", "model.layers.7.self_attn.k_proj", "model.layers.7.self_attn.v_proj", "model.layers.7.mlp.gate", "model.layers.7.mlp.shared_expert_gate", "model.layers.8.linear_attn.in_proj_qkvz", "model.layers.8.linear_attn.in_proj_ba", "model.layers.8.mlp.gate", "model.layers.8.mlp.shared_expert_gate", "model.layers.9.linear_attn.in_proj_qkvz", "model.layers.9.linear_attn.in_proj_ba", "model.layers.9.mlp.gate", "model.layers.9.mlp.shared_expert_gate", "model.layers.10.linear_attn.in_proj_qkvz", "model.layers.10.linear_attn.in_proj_ba", "model.layers.10.mlp.gate", "model.layers.10.mlp.shared_expert_gate", "model.layers.11.self_attn.q_proj", "model.layers.11.self_attn.k_proj", "model.layers.11.self_attn.v_proj", "model.layers.11.mlp.gate", "model.layers.11.mlp.shared_expert_gate", "model.layers.12.linear_attn.in_proj_qkvz", "model.layers.12.linear_attn.in_proj_ba", "model.layers.12.mlp.gate", "model.layers.12.mlp.shared_expert_gate", "model.layers.13.linear_attn.in_proj_qkvz", "model.layers.13.linear_attn.in_proj_ba", "model.layers.13.mlp.gate", "model.layers.13.mlp.shared_expert_gate", "model.layers.14.linear_attn.in_proj_qkvz", "model.layers.14.linear_attn.in_proj_ba", "model.layers.14.mlp.gate", "model.layers.14.mlp.shared_expert_gate", "model.layers.15.self_attn.q_proj", "model.layers.15.self_attn.k_proj", "model.layers.15.self_attn.v_proj", "model.layers.15.mlp.gate", "model.layers.15.mlp.shared_expert_gate", "model.layers.16.linear_attn.in_proj_qkvz", "model.layers.16.linear_attn.in_proj_ba", "model.layers.16.mlp.gate", "model.layers.16.mlp.shared_expert_gate", "model.layers.17.linear_attn.in_proj_qkvz", "model.layers.17.linear_attn.in_proj_ba", "model.layers.17.mlp.gate", "model.layers.17.mlp.shared_expert_gate", "model.layers.18.linear_attn.in_proj_qkvz", "model.layers.18.linear_attn.in_proj_ba", "model.layers.18.mlp.gate", "model.layers.18.mlp.shared_expert_gate", "model.layers.19.self_attn.q_proj", "model.layers.19.self_attn.k_proj", "model.layers.19.self_attn.v_proj", "model.layers.19.mlp.gate", "model.layers.19.mlp.shared_expert_gate", "model.layers.20.linear_attn.in_proj_qkvz", "model.layers.20.linear_attn.in_proj_ba", "model.layers.20.mlp.gate", "model.layers.20.mlp.shared_expert_gate", "model.layers.21.linear_attn.in_proj_qkvz", "model.layers.21.linear_attn.in_proj_ba", "model.layers.21.mlp.gate", "model.layers.21.mlp.shared_expert_gate", "model.layers.22.linear_attn.in_proj_qkvz", "model.layers.22.linear_attn.in_proj_ba", "model.layers.22.mlp.gate", "model.layers.22.mlp.shared_expert_gate", "model.layers.23.self_attn.q_proj", "model.layers.23.self_attn.k_proj", "model.layers.23.self_attn.v_proj", "model.layers.23.mlp.gate", "model.layers.23.mlp.shared_expert_gate", "model.layers.24.linear_attn.in_proj_qkvz", "model.layers.24.linear_attn.in_proj_ba", "model.layers.24.mlp.gate", "model.layers.24.mlp.shared_expert_gate", "model.layers.25.linear_attn.in_proj_qkvz", "model.layers.25.linear_attn.in_proj_ba", "model.layers.25.mlp.gate", "model.layers.25.mlp.shared_expert_gate", "model.layers.26.linear_attn.in_proj_qkvz", "model.layers.26.linear_attn.in_proj_ba", "model.layers.26.mlp.gate", "model.layers.26.mlp.shared_expert_gate", "model.layers.27.self_attn.q_proj", "model.layers.27.self_attn.k_proj", "model.layers.27.self_attn.v_proj", "model.layers.27.mlp.gate", "model.layers.27.mlp.shared_expert_gate", "model.layers.28.linear_attn.in_proj_qkvz", "model.layers.28.linear_attn.in_proj_ba", "model.layers.28.mlp.gate", "model.layers.28.mlp.shared_expert_gate", "model.layers.29.linear_attn.in_proj_qkvz", "model.layers.29.linear_attn.in_proj_ba", "model.layers.29.mlp.gate", "model.layers.29.mlp.shared_expert_gate", "model.layers.30.linear_attn.in_proj_qkvz", "model.layers.30.linear_attn.in_proj_ba", "model.layers.30.mlp.gate", "model.layers.30.mlp.shared_expert_gate", "model.layers.31.self_attn.q_proj", "model.layers.31.self_attn.k_proj", "model.layers.31.self_attn.v_proj", "model.layers.31.mlp.gate", "model.layers.31.mlp.shared_expert_gate", "model.layers.32.linear_attn.in_proj_qkvz", "model.layers.32.linear_attn.in_proj_ba", "model.layers.32.mlp.gate", "model.layers.32.mlp.shared_expert_gate", "model.layers.33.linear_attn.in_proj_qkvz", "model.layers.33.linear_attn.in_proj_ba", "model.layers.33.mlp.gate", "model.layers.33.mlp.shared_expert_gate", "model.layers.34.linear_attn.in_proj_qkvz", "model.layers.34.linear_attn.in_proj_ba", "model.layers.34.mlp.gate", "model.layers.34.mlp.shared_expert_gate", "model.layers.35.self_attn.q_proj", "model.layers.35.self_attn.k_proj", "model.layers.35.self_attn.v_proj", "model.layers.35.mlp.gate", "model.layers.35.mlp.shared_expert_gate", "model.layers.36.linear_attn.in_proj_qkvz", "model.layers.36.linear_attn.in_proj_ba", "model.layers.36.mlp.gate", "model.layers.36.mlp.shared_expert_gate", "model.layers.37.linear_attn.in_proj_qkvz", "model.layers.37.linear_attn.in_proj_ba", "model.layers.37.mlp.gate", "model.layers.37.mlp.shared_expert_gate", "model.layers.38.linear_attn.in_proj_qkvz", "model.layers.38.linear_attn.in_proj_ba", "model.layers.38.mlp.gate", "model.layers.38.mlp.shared_expert_gate", "model.layers.39.self_attn.q_proj", "model.layers.39.self_attn.k_proj", "model.layers.39.self_attn.v_proj", "model.layers.39.mlp.gate", "model.layers.39.mlp.shared_expert_gate", "model.layers.40.linear_attn.in_proj_qkvz", "model.layers.40.linear_attn.in_proj_ba", "model.layers.40.mlp.gate", "model.layers.40.mlp.shared_expert_gate", "model.layers.41.linear_attn.in_proj_qkvz", "model.layers.41.linear_attn.in_proj_ba", "model.layers.41.mlp.gate", "model.layers.41.mlp.shared_expert_gate", "model.layers.42.linear_attn.in_proj_qkvz", "model.layers.42.linear_attn.in_proj_ba", "model.layers.42.mlp.gate", "model.layers.42.mlp.shared_expert_gate", "model.layers.43.self_attn.q_proj", "model.layers.43.self_attn.k_proj", "model.layers.43.self_attn.v_proj", "model.layers.43.mlp.gate", "model.layers.43.mlp.shared_expert_gate", "model.layers.44.linear_attn.in_proj_qkvz", "model.layers.44.linear_attn.in_proj_ba", "model.layers.44.mlp.gate", "model.layers.44.mlp.shared_expert_gate", "model.layers.45.linear_attn.in_proj_qkvz", "model.layers.45.linear_attn.in_proj_ba", "model.layers.45.mlp.gate", "model.layers.45.mlp.shared_expert_gate", "model.layers.46.linear_attn.in_proj_qkvz", "model.layers.46.linear_attn.in_proj_ba", "model.layers.46.mlp.gate", "model.layers.46.mlp.shared_expert_gate", "model.layers.47.self_attn.q_proj", "model.layers.47.self_attn.k_proj", "model.layers.47.self_attn.v_proj", "model.layers.47.mlp.gate", "model.layers.47.mlp.shared_expert_gate", "lm_head" ], "export": { "kv_cache_group": [], "min_kv_scale": 0.0, "pack_method": "reorder", "weight_format": "real_quantized", "weight_merge_groups": null }, "global_quant_config": { "bias": null, "input_tensors": { "ch_axis": -1, "dtype": "fp4", "group_size": 32, "is_dynamic": true, "is_scale_quant": false, "mx_element_dtype": null, "observer_cls": "PerBlockMXObserver", "qscheme": "per_group", "round_method": "half_even", "scale_calculation_mode": "even", "scale_format": "e8m0", "scale_type": "float", "symmetric": null }, "output_tensors": null, "target_device": null, "weight": { "ch_axis": -1, "dtype": "fp4", "group_size": 32, "is_dynamic": false, "is_scale_quant": false, "mx_element_dtype": null, "observer_cls": "PerBlockMXObserver", "qscheme": "per_group", "round_method": "half_even", "scale_calculation_mode": "even", "scale_format": "e8m0", "scale_type": "float", "symmetric": null } }, "kv_cache_post_rope": false, "kv_cache_quant_config": {}, "layer_quant_config": {}, "layer_type_quant_config": {}, "quant_method": "quark", "quant_mode": "eager_mode", "softmax_quant_spec": null, "version": "0.12+86d5498526" }, "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 }