{
  "transformers_version": "5.14.1",
  "architectures": null,
  "output_hidden_states": false,
  "return_dict": true,
  "dtype": null,
  "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": 1024,
  "hidden_size": 216,
  "intermediate_size": 540,
  "num_hidden_layers": 4,
  "num_attention_heads": 8,
  "num_key_value_heads": 1,
  "hidden_act": "silu",
  "max_position_embeddings": 1024,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "use_cache": false,
  "tie_word_embeddings": true,
  "rope_parameters": {
    "rope_type": "default",
    "rope_theta": 10000000.0,
    "partial_rotary_factor": 0.25
  },
  "attention_bias": false,
  "attention_dropout": 0.0,
  "head_dim": 56,
  "linear_conv_kernel_dim": 4,
  "linear_key_head_dim": 54,
  "linear_value_head_dim": 54,
  "linear_num_key_heads": 4,
  "linear_num_value_heads": 8,
  "decoder_sparse_step": 1,
  "moe_intermediate_size": 54,
  "shared_expert_intermediate_size": 54,
  "num_experts_per_tok": 2,
  "num_experts": 8,
  "norm_topk_prob": true,
  "output_router_logits": true,
  "router_aux_loss_coef": 0.01,
  "mlp_only_layers": [],
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention"
  ],
  "pad_token_id": 1000,
  "bos_token_id": 1000,
  "eos_token_id": 1001,
  "_name_or_path": "",
  "use_sliding_window": false,
  "sliding_window": null,
  "partial_rotary_factor": 0.25,
  "model_type": "qwen3_next",
  "output_attentions": false
}