{
  "activation_function": "gelu_new",
  "architectures": [
    "GPT2ForTokenClassification"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 1,
  "custom_pipelines": {
    "upos": {
      "impl": "upos.BellmanFordTokenClassificationPipeline",
      "pt": "AutoModelForTokenClassification"
    }
  },
  "embd_pdrop": 0.1,
  "eos_token_id": 2,
  "id2label": {
    "0": "ADJ",
    "1": "B-ADJ",
    "2": "I-ADJ",
    "3": "ADJ|Polarity=Neg",
    "4": "B-ADJ|Polarity=Neg",
    "5": "I-ADJ|Polarity=Neg",
    "6": "ADP",
    "7": "B-ADP",
    "8": "I-ADP",
    "9": "ADV",
    "10": "B-ADV",
    "11": "I-ADV",
    "12": "AUX",
    "13": "B-AUX",
    "14": "I-AUX",
    "15": "AUX|Polarity=Neg",
    "16": "B-AUX|Polarity=Neg",
    "17": "I-AUX|Polarity=Neg",
    "18": "CCONJ",
    "19": "B-CCONJ",
    "20": "I-CCONJ",
    "21": "DET",
    "22": "B-DET",
    "23": "I-DET",
    "24": "INTJ",
    "25": "B-INTJ",
    "26": "I-INTJ",
    "27": "NOUN",
    "28": "B-NOUN",
    "29": "I-NOUN",
    "30": "NOUN|Polarity=Neg",
    "31": "B-NOUN|Polarity=Neg",
    "32": "I-NOUN|Polarity=Neg",
    "33": "NUM",
    "34": "B-NUM",
    "35": "I-NUM",
    "36": "PART",
    "37": "B-PART",
    "38": "I-PART",
    "39": "PRON",
    "40": "B-PRON",
    "41": "I-PRON",
    "42": "PROPN",
    "43": "B-PROPN",
    "44": "I-PROPN",
    "45": "PUNCT",
    "46": "B-PUNCT",
    "47": "I-PUNCT",
    "48": "SCONJ",
    "49": "B-SCONJ",
    "50": "I-SCONJ",
    "51": "SYM",
    "52": "B-SYM",
    "53": "I-SYM",
    "54": "VERB",
    "55": "B-VERB",
    "56": "I-VERB",
    "57": "X",
    "58": "B-X",
    "59": "I-X"
  },
  "initializer_range": 0.02,
  "label2id": {
    "ADJ": 0,
    "ADJ|Polarity=Neg": 3,
    "ADP": 6,
    "ADV": 9,
    "AUX": 12,
    "AUX|Polarity=Neg": 15,
    "B-ADJ": 1,
    "B-ADJ|Polarity=Neg": 4,
    "B-ADP": 7,
    "B-ADV": 10,
    "B-AUX": 13,
    "B-AUX|Polarity=Neg": 16,
    "B-CCONJ": 19,
    "B-DET": 22,
    "B-INTJ": 25,
    "B-NOUN": 28,
    "B-NOUN|Polarity=Neg": 31,
    "B-NUM": 34,
    "B-PART": 37,
    "B-PRON": 40,
    "B-PROPN": 43,
    "B-PUNCT": 46,
    "B-SCONJ": 49,
    "B-SYM": 52,
    "B-VERB": 55,
    "B-X": 58,
    "CCONJ": 18,
    "DET": 21,
    "I-ADJ": 2,
    "I-ADJ|Polarity=Neg": 5,
    "I-ADP": 8,
    "I-ADV": 11,
    "I-AUX": 14,
    "I-AUX|Polarity=Neg": 17,
    "I-CCONJ": 20,
    "I-DET": 23,
    "I-INTJ": 26,
    "I-NOUN": 29,
    "I-NOUN|Polarity=Neg": 32,
    "I-NUM": 35,
    "I-PART": 38,
    "I-PRON": 41,
    "I-PROPN": 44,
    "I-PUNCT": 47,
    "I-SCONJ": 50,
    "I-SYM": 53,
    "I-VERB": 56,
    "I-X": 59,
    "INTJ": 24,
    "NOUN": 27,
    "NOUN|Polarity=Neg": 30,
    "NUM": 33,
    "PART": 36,
    "PRON": 39,
    "PROPN": 42,
    "PUNCT": 45,
    "SCONJ": 48,
    "SYM": 51,
    "VERB": 54,
    "X": 57
  },
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_embd": 1280,
  "n_head": 20,
  "n_inner": null,
  "n_layer": 36,
  "n_positions": 1024,
  "pad_token_id": 1,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "tokenizer_class": "GPT2Tokenizer",
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "vocab_size": 6000
}