config.json

{
  "_name_or_path": "bert-base-multilingual-cased",
  "architectures": [
    "BertForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "directionality": "bidi",
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "too-strict\n",
    "1": "ok\n",
    "2": "too-loose\n",
    "3": "not-applicable\n"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "not-applicable\n": 3,
    "ok\n": 1,
    "too-loose\n": 2,
    "too-strict\n": 0
  },
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "pooler_fc_size": 768,
  "pooler_num_attention_heads": 12,
  "pooler_num_fc_layers": 3,
  "pooler_size_per_head": 128,
  "pooler_type": "first_token_transform",
  "type_vocab_size": 2,
  "vocab_size": 119547
}