tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "!",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100000": {
      "content": "<｜begin▁of▁sentence｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100001": {
      "content": "<｜end▁of▁sentence｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100002": {
      "content": "ø",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100003": {
      "content": "ö",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100004": {
      "content": "ú",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100005": {
      "content": "ÿ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100006": {
      "content": "õ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100007": {
      "content": "÷",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100008": {
      "content": "û",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100009": {
      "content": "ý",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100010": {
      "content": "À",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100011": {
      "content": "ù",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100012": {
      "content": "Á",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100013": {
      "content": "þ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100014": {
      "content": "ü",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100015": {
      "content": "<|EOT|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<｜begin▁of▁sentence｜>",
  "chat_template": "{{ bos_token }}{% for message in messages %}\n{% if message['from'] == 'human' %}\n{{ '<|user|>\n' + message['value']}}\n{% elif message['from'] == 'system' %}\n{{ '<|system|>\n' + message['value']}}\n{% elif message['from'] == 'gpt' %}\n{{ '<|assistant|>\n'  + message['value'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|EOT|>",
  "legacy": true,
  "model_max_length": 4096,
  "pad_token": "!",
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": null,
  "use_default_system_prompt": false
}