tokenizer_config.json

{
  "bos_token": {
    "__type": "AddedToken",
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 2048,
  "pad_token": {
    "__type": "AddedToken",
    "content": "<pad>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "padding_side": "right",
  "special_tokens_map_file": "./checkpoints/baichuan_7B_clean/special_tokens_map.json",
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}