tokenizer/config.json

{
  "vocab_size": 8192,
  "special_tokens": {
    "pad_token": "<|pad|>",
    "bos_token": "<|bos|>",
    "eos_token": "<|eos|>",
    "unk_token": "<|unk|>"
  },
  "pad_id": 0,
  "bos_id": 1,
  "eos_id": 2,
  "unk_id": 3
}