config.json

{
  "_name_or_path": "/home/paperspace/MLM/tests/local_checkpoints/medialbertina_ptpt_full",
  "architectures": [
    "DebertaV2ForTokenClassification"
  ],
  "attention_head_size": 64,
  "attention_probs_dropout_prob": 0.1,
  "conv_act": "gelu",
  "conv_kernel_size": 3,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1536,
  "id2label": {
    "0": "O",
    "1": "B-D",
    "2": "I-D",
    "3": "B-S",
    "4": "I-S",
    "5": "B-M",
    "6": "I-M",
    "7": "B-DO",
    "8": "I-DO",
    "9": "B-PM",
    "10": "I-PM",
    "11": "B-SV",
    "12": "I-SV",
    "13": "B-R",
    "14": "I-R",
    "15": "B-P",
    "16": "I-P"
  },
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "label2id": {
    "B-D": 1,
    "B-DO": 7,
    "B-M": 5,
    "B-P": 15,
    "B-PM": 9,
    "B-R": 13,
    "B-S": 3,
    "B-SV": 11,
    "I-D": 2,
    "I-DO": 8,
    "I-M": 6,
    "I-P": 16,
    "I-PM": 10,
    "I-R": 14,
    "I-S": 4,
    "I-SV": 12,
    "O": 0
  },
  "layer_norm_eps": 1e-07,
  "max_position_embeddings": 512,
  "max_relative_positions": -1,
  "model_type": "deberta-v2",
  "norm_rel_ebd": "layer_norm",
  "num_attention_heads": 24,
  "num_hidden_layers": 24,
  "pad_token_id": 0,
  "pooler_dropout": 0,
  "pooler_hidden_act": "gelu",
  "pooler_hidden_size": 1536,
  "pos_att_type": [
    "p2c",
    "c2p"
  ],
  "position_biased_input": false,
  "position_buckets": 256,
  "relative_attention": true,
  "share_att_key": true,
  "torch_dtype": "float32",
  "transformers_version": "4.36.2",
  "type_vocab_size": 0,
  "vocab_size": 128100
}