config.json

{
  "architectures": [
    "Qwen3ForSequenceClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "dtype": "float32",
  "eos_token_id": 151643,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "id2label": {
    "0": "utility",
    "1": "evidence"
  },
  "initializer_range": 0.02,
  "intermediate_size": 17408,
  "label2id": {
    "evidence": 1,
    "utility": 0
  },
  "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",
    "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": 40,
  "model_type": "qwen3",
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "pad_token_id": 151643,
  "problem_type": "regression",
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.6",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 151936
}