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": "<|end_of_turn|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "<|pad_0|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|end_of_turn|>",
    "<|pad_0|>"
  ],
  "bos_token": "<s>",
  "chat_template": "{% set roles = { 'system': 'system', 'user': 'user', 'bot': 'assistant', 'assistant': 'assistant' } %} {% if messages[0]['role'] == 'system' %} {% set system_message = messages[0]['content'] | trim + '<|end_of_turn|>' %} {% set messages = messages[1:] %} {% else %} {% set system_message = '' %} {% endif %} {{ bos_token + system_message }} {% for message in messages %} {% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %} {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }} {% endif %} {{ 'GPT4 Correct ' + roles[message['role']] | capitalize + ': ' + message['content'] + '<|end_of_turn|>' }} {% endfor %} {% if add_generation_prompt %} {{ 'GPT4 Correct Assistant:' }} {% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|end_of_turn|>",
  "legacy": true,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": null,
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": true
}