This is probably due to the way larger numbers are tokenised, as big numbers can be split up into arbitrary forms. Take the integer 123456789. A BPE tokenizer (e.g., GPT-style) might split it like: ‘123’ ‘456’ ‘789’ or: ‘12’ ‘345’ ‘67’ ‘89’
Head teacher Michael Polly, played by David Morissey, is the prime suspect in his wife's disappearance
Go to technology，这一点在新收录的资料中也有详细论述
“I’m wondering too, I’d like to know whether I can sleep or not.”，更多细节参见新收录的资料
When you put them in the formula:
FFmpeg at Meta: Media Processing at Scale，更多细节参见新收录的资料