tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|startoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<|unk|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|startoftext|>",
  "chat_template": "{% set bom_token='<|bom|>' %}{% set eom_token='<|eom|>' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a task following system, respond to the user\\'s input precisely. Do not add any additional information.' %}{% endif %}{{ bom_token + 'System: ' + system_message + eom_token + '' }}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ bom_token + 'User: ' + content.strip() + eom_token }}{% elif message['role'] == 'system' %}{{ bom_token + 'System: ' + content.strip() + eom_token }}{% elif message['role'] == 'assistant' %}{{ bom_token + 'Assistant: ' + content.strip() + eom_token }}{% endif %}{% if message['role'] == 'assistant' and loop.index0 == loop.length - 1 %}{{ 'User: ' }}{% elif message['role'] == 'user' and loop.index0 == loop.length - 1 %}{{ '' + bom_token + 'Assistant:' }}{% else %}{{ '' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|pad|>",
  "spaces_between_special_tokens": false,
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<|unk|>",
  "use_default_system_prompt": false
}