tokenizer_config.json

{
  "add_prefix_space": false,
  "bos_token": "<|endoftext|>",
  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% elif message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "model_max_length": 512,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}