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": "▁<PRE>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "▁<MID>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32002": {
      "content": "▁<SUF>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32003": {
      "content": "▁<EOT>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "▁<PRE>",
    "▁<MID>",
    "▁<SUF>",
    "▁<EOT>"
  ],
  "bos_token": "<s>",
  "chat_template": "{% if messages[0]['role'] == 'system' %}\n        {% set loop_messages = messages[1:] %}\n        {% set system_message = '<<SYS>>\n' + messages[0]['value'].strip() + '\n<</SYS>>\n\n' %}\n    {% else %}\n        {% set loop_messages = messages %}\n        {% set system_message = '' %}\n    {% endif %}\n\n    {% for message in loop_messages %}\n        {% if (message['role'] == 'human') != (loop.index0 % 2 == 0) %}{% endif %}\n    \n        {% if loop.index0 == 0 %}\n            {% set content = system_message + message['value'] %}\n        {% else %}\n            {% set content = message['value'] %}\n        {% endif %}\n    \n        {% if message['role'] == 'human' %}\n            {{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}\n        {% elif message['role'] == 'gpt' %}\n            {{ ' '  + content.strip() + ' ' + eos_token }}\n        {% endif %}\n    {% endfor %} ",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "eot_token": "▁<EOT>",
  "fill_token": "<FILL_ME>",
  "legacy": null,
  "middle_token": "▁<MID>",
  "model_max_length": 2048,
  "pad_token": "<unk>",
  "prefix_token": "▁<PRE>",
  "sp_model_kwargs": {},
  "suffix_token": "▁<SUF>",
  "tokenizer_class": "CodeLlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}