tokenizer_config.json

{
  "vocab_size": 32000,
  "model_type": "BPE",
  "special_tokens": {
    "pad_token": "<pad>",
    "bos_token": "<s>",
    "eos_token": "</s>",
    "unk_token": "<unk>",
    "mask_token": "<mask>"
  },
  "pad_token_id": 0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "unk_token_id": 3
}