tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "add_prefix_space": true,
  "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
    },
    "64000": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "chat_template": "{{ bos_token }}{% if messages[0]['from'] == 'system' %}{% if messages[1]['from'] == 'human' %}{{ '[INST] ' + messages[0]['value'] + ' ' + messages[1]['value'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ '[INST] ' + messages[0]['value'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['from'] == 'human' %}{{ '[INST] ' + message['value'] + ' [/INST]' }}{% elif message['from'] == 'gpt' %}{{ message['value'] + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "legacy": true,
  "model_max_length": 262144,
  "pad_token": "[PAD]",
  "padding_side": "left",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}