@lenml/tokenizer-gpt4/models/tokenizer_config.json

gpt4 tokenizer for NodeJS/Browser

{
  "add_prefix_space": false,
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "model_max_length": 8192,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>",
  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
}