tokenizer_config.json

{
  "added_tokens_decoder": {
    "2": {
      "content": "<|startoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<|end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": "<|mdm_mask|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|system|>",
    "<|user|>",
    "<|assistant|>",
    "<|end|>",
    "<|mdm_mask|>"
  ],
  "assistant_token": "<|assistant|>",
  "bos_token": "<|startoftext|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "eot_token": "<|end|>",
  "extra_special_tokens": {},
  "mask_token": "<|mdm_mask|>",
  "model_max_length": 4096,
  "pad_token": "<|endoftext|>",
  "padding_side": "right",
  "system_token": "<|system|>",
  "tokenizer_class": "CharTokenizer",
  "unk_token": null,
  "user_token": "<|user|>",
  "auto_map": {
    "AutoTokenizer": [
      "char_tokenizer.CharTokenizer",
      null
    ]
  }
}