{
  "_name_or_path": "ai-forever/mGPT",
  "activation_function": "gelu_new",
  "architectures": [
    "GPT2ForTokenClassification"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "gradient_checkpointing": false,
  "id2label": {
    "0": "B-LOC",
    "1": "B-MISC",
    "2": "B-ORG",
    "3": "B-PERS",
    "4": "I-LOC",
    "5": "I-MISC",
    "6": "I-ORG",
    "7": "I-PERS",
    "8": "O"
  },
  "initializer_range": 0.02,
  "label2id": {
    "B-LOC": 0,
    "B-MISC": 1,
    "B-ORG": 2,
    "B-PERS": 3,
    "I-LOC": 4,
    "I-MISC": 5,
    "I-ORG": 6,
    "I-PERS": 7,
    "O": 8
  },
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_ctx": 2048,
  "n_embd": 2048,
  "n_head": 16,
  "n_inner": null,
  "n_layer": 24,
  "n_positions": 2048,
  "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,
  "torch_dtype": "float32",
  "transformers_version": "4.28.0",
  "use_cache": true,
  "vocab_size": 100001
}