tokenizer_config.json

{
  "added_tokens_decoder": {},
  "additional_special_tokens": [
    "<|startoftext|>",
    "<|extra_0|>",
    "<|extra_4|>",
    "<|extra_5|>",
    "<|eos|>"
  ],
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_hy.HYTokenizer",
      null
    ]
  },
  "chat_template": "{% set context = {'has_head': true} %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = message['content'] %}{% if loop.index0 == 0 %}{% if content == '' %}{% set _ = context.update({'has_head': false}) %}{% elif message['role'] == 'system' %}{% set content = '<|startoftext|>' + content + '<|extra_4|>' %}{% endif %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 1 and not context.has_head %}{% set content = '<|startoftext|>' + content %}{% endif %}{% if loop.index0 == 1 and context.has_head %}{% set content = content + '<|extra_0|>' %}{% else %}{% set content = '<|startoftext|>' + content + '<|extra_0|>' %}{% endif %}{% elif message['role'] == 'assistant' %}{% set content = content + '<|eos|>' %}{% endif %}{{ content }}{% endfor %}",
  "clean_up_tokenization_spaces": true,
  "model_max_length": 1048576,
  "model_type": "gpt2",
  "pad_token": "<|pad|>",
  "tokenizer_class": "HYTokenizer"
}