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": "<CLS>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "<SEP>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32002": {
      "content": "<EOD>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32003": {
      "content": "<MASK>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32004": {
      "content": "<PAD>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32005": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32006": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "bos_token": "<s>",
  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{%- if not messages|selectattr('role', 'equalto', 'function_metadata')|list %}<|im_start|>system\n{{ message['content'] }}<|im_end|>\n{%- else %}<|im_start|>system\n{{ message['content'] }}{%- endif %}{% elif message['role'] == 'function_metadata' and loop.index0 == 1 %}\nYou have access to the following functions. Use them if required:\n\n{{ message['content'] }}\n\n<|im_end|>\n{% elif message['role'] == 'function_metadata' and loop.index0 == 0 %}<|im_start|>system\nYou have access to the following functions. Use them if required:\n\n{{ message['content'] }}\n\n<|im_end|>\n{% elif message['role'] == 'assistant' %}<|im_end|>\n<|im_start|>assistant\n{{ message['content'] }}{{ eos_token }}{% elif message['role'] == 'function_call' %}<|im_end|>\n<|im_start|>assistant\n[FUNCTION_CALL] {{ message['content'] }}{{ eos_token }}{% elif message['role'] == 'function_response' %}<|im_start|>user\n[FUNCTION_RESPONSE] Here is the response to the function call. If helpful, use it to respond to the user's question:{{ message['content'] }}{% elif message['role'] == 'user'%}<|im_start|>user\n{{ message['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_end|>\n<|im_start|>assistant\n{% endif %}",
  "clean_up_tokenization_spaces": false,
  "cls_token": "<CLS>",
  "eos_token": "<|im_end|>",
  "legacy": false,
  "mask_token": "<MASK>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<PAD>",
  "padding_side": "right",
  "sep_token": "<SEP>",
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}