special_tokens_map.json

{
  "additional_special_tokens": [
    "<|im_start|>",
    "<|im_end|>"
  ],
  "eos_token": {
    "content": "<|im_end|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "pad_token": {
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  }
}
{text = re.sub(r'\*\*(.*?)\*\*', r'\1', text)
    text = re.sub(r'(\*|_)(.*?)\1', r'\2', text)
    text = re.sub(r'`(.*?)`', r'\1', text)
    text = re.sub(r'^#+\s+', '', text, flags=re.MULTILINE)
    return text}