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": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "<|im_start|>system",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32002": {
      "content": "<|im_start|>user",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32003": {
      "content": "<|im_start|>assistant",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32004": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|im_start|>system",
    "<|im_start|>user",
    "<|im_start|>assistant",
    "<|im_end|>"
  ],
  "bos_token": "<s>",
  "chat_template": "\n    {% for message in messages %}\n    {% if message['role'] == 'user' %}\n    {{'<|im_start|>user\n' + message['content'].strip() + '<|im_end|>' }}\n    {% elif message['role'] == 'system' %}\n    {{'<|im_start|>system\n' + message['content'].strip() + '<|im_end|>' }}\n    {% elif message['role'] == 'assistant' %}\n    {{'<|im_start|>assistant\n'  + message['content'] + '<|im_end|>' }}\n    {% endif %}\n    {% endfor %}\n    ",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "legacy": true,
  "max_length": 2048,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "[PAD]",
  "padding_side": "right",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "stride": 0,
  "tokenizer_class": "LlamaTokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}