tokenizer_config.json

{
  "add_prefix_space": false,
  "add_bos_token": false,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>",
  "bos_token": "<|endoftext|>",
  "eos_token": "<|endoftext|>",
  "model_max_length": 1000000000000000019884624838656,
  "clean_up_tokenization_spaces": true,
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{{ '<|im_start|>' + 'system' + '\\n' + system_message + '<|im_end|>' + '\\n' }}{% for message in loop_messages %}{{ '<|im_start|>' + message['role'] + '\\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>' + 'assistant' + '\\n' }}{% endif %}"
}