tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32000": {
      "content": "<|eot|>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "<|eof|>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "32002": {
      "content": "<|bof|>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<unk>",
    "<s>",
    "</s>",
    "<|eot|>",
    "<|eof|>",
    "<|bof|>"
  ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "legacy": true,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": null,
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "LlamaTokenizer",
  "tokenizer_file": "/workspace/Mistral-7B-v0.1/tokenizer.json",
  "unk_token": "<unk>",
  "use_default_system_prompt": true
}