tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "50256": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|endoftext|>",
  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "model_max_length": 1024,
  "pad_token": "<|endoftext|>",
  "padding_side": "left",
  "split_special_tokens": false,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}