config.json

{
  "architectures": [
    "Qwen3ForSequenceClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "classifier_from_token": [
    "no",
    "yes"
  ],
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2560,
  "id2label": {
    "0": "LABEL_0"
  },
  "initializer_range": 0.02,
  "intermediate_size": 9728,
  "is_original_qwen3_reranker": false,
  "label2id": {
    "LABEL_0": 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"
  ],
  "max_position_embeddings": 40960,
  "max_window_layers": 36,
  "method": "from_2_way_softmax",
  "model_type": "qwen3",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "num_labels": 1,
  "pad_token_id": 151643,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "float32",
  "transformers_version": "4.55.0",
  "use_cache": true,
  "use_pad_token": false,
  "use_sliding_window": false,
  "vocab_size": 151669
}