tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<|startofinstruction|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": true,
  "eos_token": {
    "__type": "AddedToken",
    "content": "<|endofcompletion|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "errors": "replace",
  "model_max_length": 1024,
  "pad_token": {
    "__type": "AddedToken",
    "content": "<|pad|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "sep_token": "<|endofinstruction|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{bos_token + message['content'].strip() + sep_token}}{% elif message['role'] == 'assistant' %}{{message['content'].strip() + eos_token}}{% endif %}{% endfor %}",
  "use_default_system_prompt": false
}