tokenizers/tokenizer.json

{
  "added_tokens": [],
  "decoder_start_token_id": 0,
  "do_lower_case": true,
  "embedding_size": 768,
  "max_len": 512,
  "model_input_names": ["input_ids", "attention_mask"],
  "pad_token_id": 0,
  "special_tokens": {
    "unk_token": "<unk>",
    "pad_token": "<pad>",
    "bos_token": "<bos>",
    "eos_token": "<eos>"
  },
  "tokenizer_class": "BertTokenizer",
  "vocab_size": 30522
}