config.json

{
  "architectures": [
    "Qwen3ForSequenceClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "dtype": "bfloat16",
  "eos_token_id": 151643,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "id2label": {
    "0": "question",
    "1": "simple_reflection",
    "2": "complex_reflection",
    "3": "giving_info_or_pwp"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "complex_reflection": 2,
    "giving_info_or_pwp": 3,
    "question": 0,
    "simple_reflection": 1
  },
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen3",
  "num_attention_heads": 16,
  "num_hidden_layers": 28,
  "num_key_value_heads": 8,
  "pad_token_id": 151643,
  "problem_type": "multi_label_classification",
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "transformers_version": "4.56.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151669
}