tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": ">>TITLE<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": ">>ABSTRACT<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": ">>INTRODUCTION<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": ">>SUMMARY<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": ">>COMMENT<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": ">>ANSWER<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": ">>QUESTION<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": ">>DOMAIN<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": ">>PREFIX<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "9": {
      "content": ">>SUFFIX<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "10": {
      "content": ">>MIDDLE<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "11": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65020": {
      "content": "<end_message>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65021": {
      "content": "<start_assistant>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65022": {
      "content": "<start_user>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65023": {
      "content": "<start_system>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    ">>TITLE<<",
    ">>ABSTRACT<<",
    ">>INTRODUCTION<<",
    ">>SUMMARY<<",
    ">>COMMENT<<",
    ">>ANSWER<<",
    ">>QUESTION<<",
    ">>DOMAIN<<",
    ">>PREFIX<<",
    ">>SUFFIX<<",
    ">>MIDDLE<<",
    "<start_system>",
    "<start_user>",
    "<start_assistant>",
    "<end_message>"
  ],
  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<start_user>' + message['content'].strip() + '<end_message>' }}{% elif message['role'] == 'system' %}{{ '<start_system>' + message['content'].strip() + '<end_message>' }}{% elif message['role'] == 'assistant' %}{{ '<start_assistant>'  + message['content'] + '<end_message>' }}{% else %}{{ raise_exception('Only system, user and assistant roles are supported.') }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<start_assistant>' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<end_message>",
  "model_max_length": 8192,
  "tokenizer_class": "PreTrainedTokenizerFast"
}