| { |
| "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, |
| "original_num_experts": 512, |
| "output_router_logits": false, |
| "partial_rotary_factor": 0.25, |
| "per_layer_num_experts": [ |
| 308, |
| 218, |
| 328, |
| 281, |
| 285, |
| 316, |
| 300, |
| 277, |
| 268, |
| 270, |
| 286, |
| 298, |
| 274, |
| 268, |
| 272, |
| 285, |
| 282, |
| 281, |
| 275, |
| 264, |
| 262, |
| 238, |
| 237, |
| 255, |
| 238, |
| 268, |
| 262, |
| 240, |
| 248, |
| 272, |
| 236, |
| 269, |
| 247, |
| 215, |
| 240, |
| 237, |
| 257, |
| 274, |
| 259, |
| 245, |
| 255, |
| 200, |
| 210, |
| 217, |
| 209, |
| 219, |
| 181, |
| 162 |
| ], |
| "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": "4.57.6", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
|
|