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
    },
    "46331": {
      "content": "<|sep|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "46332": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "46333": {
      "content": "<|acc|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "46334": {
      "content": "<|rrn|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "46335": {
      "content": "<|tel|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "46336": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "46337": {
      "content": "<<SYS>>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": true,
      "special": false
    },
    "46338": {
      "content": "<</SYS>>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": true,
      "special": false
    },
    "46339": {
      "content": "[INST]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": true,
      "special": false
    },
    "46340": {
      "content": "[/INST]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": true,
      "special": false
    },
    "46341": {
      "content": "<<DOC>>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": true,
      "special": false
    },
    "46342": {
      "content": "<</DOC>>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": true,
      "special": false
    },
    "46343": {
      "content": "<<D>>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": true,
      "special": false
    },
    "46344": {
      "content": "<</D>>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": true,
      "special": false
    },
    "46345": {
      "content": " ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "legacy": false,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|pad|>",
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": true
}