| { |
| "architectures": [ |
| "Qwen3NextForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0, |
| "bos_token_id": 151643, |
| "decoder_sparse_step": 1, |
| "eos_token_id": 151645, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 5120, |
| "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": { |
| "group_size": 64, |
| "bits": 2, |
| "mode": "affine", |
| "model.layers.0.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 2, |
| "mode": "affine", |
| "model.layers.0.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.0.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.shared_expert_gate": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "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, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.57.0.dev0", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
