tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "199999": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200018": {
      "content": "<|endofprompt|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200019": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200020": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|im_start|>",
    "<|im_end|>"
  ],
  "bos_token": "<|endoftext|>",
  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '\n<|im_end|>' + '\n'}}{% endfor %}{{ '<|im_start|>assistant\n' }}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "model_max_length": 128000,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}