{
  "architectures": [
    "GPTNeoXForSequenceClassification"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "classifier_dropout": 0.1,
  "dtype": "float32",
  "eos_token_id": 0,
  "hidden_act": "gelu",
  "hidden_dropout": 0.0,
  "hidden_size": 2560,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4",
    "5": "LABEL_5",
    "6": "LABEL_6",
    "7": "LABEL_7",
    "8": "LABEL_8",
    "9": "LABEL_9"
  },
  "initializer_range": 0.02,
  "intermediate_size": 10240,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6,
    "LABEL_7": 7,
    "LABEL_8": 8,
    "LABEL_9": 9
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "gpt_neox",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "pad_token_id": 0,
  "partial_rotary_factor": 0.25,
  "problem_type": "single_label_classification",
  "rope_scaling": null,
  "rope_theta": 10000,
  "rotary_emb_base": 10000,
  "rotary_pct": 0.25,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.6",
  "use_cache": false,
  "use_parallel_residual": true,
  "vocab_size": 50304
}