| { |
| "transformers_version": "5.16.1", |
| "architectures": [ |
| "Qwen3NextForCausalLM" |
| ], |
| "output_hidden_states": false, |
| "return_dict": true, |
| "dtype": "bfloat16", |
| "chunk_size_feed_forward": 0, |
| "is_encoder_decoder": false, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "problem_type": null, |
| "vocab_size": 151936, |
| "hidden_size": 2048, |
| "intermediate_size": 5120, |
| "num_hidden_layers": 48, |
| "num_attention_heads": 16, |
| "num_key_value_heads": 2, |
| "hidden_act": "silu", |
| "max_position_embeddings": 262144, |
| "initializer_range": 0.02, |
| "rms_norm_eps": 1e-06, |
| "use_cache": true, |
| "tie_word_embeddings": false, |
| "rope_parameters": { |
| "rope_theta": 5000000, |
| "partial_rotary_factor": 0.25, |
| "rope_type": "default" |
| }, |
| "attention_bias": false, |
| "attention_dropout": 0, |
| "head_dim": 256, |
| "linear_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_value_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 32, |
| "decoder_sparse_step": 1, |
| "moe_intermediate_size": 512, |
| "shared_expert_intermediate_size": 512, |
| "num_experts_per_tok": 10, |
| "num_experts": 512, |
| "norm_topk_prob": true, |
| "output_router_logits": false, |
| "router_aux_loss_coef": 0.001, |
| "mlp_only_layers": [], |
| "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" |
| ], |
| "pad_token_id": null, |
| "bos_token_id": 151643, |
| "eos_token_id": 151645, |
| "_name_or_path": "Qwen/Qwen3-Coder-Next", |
| "model_type": "qwen3_next", |
| "partial_rotary_factor": 0.25, |
| "use_sliding_window": false, |
| "output_attentions": false, |
| "quantization_config": { |
| "quant_method": "cq", |
| "pcq_layout": "native_vllm" |
| } |
| } |
