config.json

{
  "architectures": [
    "PawQwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "disable_linear_regularization_term": false,
  "enable_ada_sparsity": true,
  "enable_lambda_task": true,
  "enable_layerwise_sparsity": false,
  "eos_token_id": 151645,
  "erank_analysis_path": "/",
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 9728,
  "layerwise_sparsity_max_ratio": 1.0,
  "layerwise_sparsity_min_ratio": 0.5,
  "layerwise_sparsity_power": 1.0,
  "layerwise_sparsity_schedule": "high-low-high",
  "layerwise_sparsity_weight": 1.0,
  "local_window_size": 2048,
  "max_position_embeddings": 262144,
  "max_window_layers": 36,
  "model_type": "qwen3",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "pooling_mode": "ctx_q",
  "pooling_seq": true,
  "retrieval_mode": "full",
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "factor": 8.0,
    "original_max_position_embeddings": 40960,
    "rope_type": "yarn",
    "type": "yarn"
  },
  "rope_theta": 1000000,
  "sink_size": 128,
  "sliding_window": null,
  "suggested_sparsity": null,
  "suggested_threshold": 0.9999070130288601,
  "tie_word_embeddings": true,
  "toggle_type": "streaming",
  "topk_k": 2048,
  "torch_dtype": "float32",
  "transformers_version": "4.51.1",
  "triangle_n_last": 128,
  "use_cache": true,
  "use_sliding_window": false,
  "use_softmax": true,
  "use_task_emb_for_mask": false,
  "vocab_size": 151936
}