{ "note": "v4 sink tokens orphaned in this surgical tokenizer; suppress at generation as belt-and-suspenders (surgical tokenizer already stops them appearing as input keys)", "bad_words_ids": [ [ 509 ], [ 1082 ], [ 1093 ], [ 1641 ], [ 2965 ], [ 3275 ], [ 4126 ], [ 4835 ], [ 5301 ], [ 7666 ], [ 7980 ], [ 8129 ], [ 8208 ], [ 8477 ], [ 10191 ], [ 10851 ], [ 11470 ], [ 15211 ], [ 16321 ], [ 17796 ], [ 19001 ], [ 24821 ], [ 25066 ], [ 25080 ], [ 25401 ], [ 25790 ], [ 25998 ], [ 26515 ], [ 27144 ], [ 27202 ], [ 27821 ], [ 27885 ], [ 28028 ], [ 28432 ], [ 28659 ], [ 29294 ], [ 31270 ], [ 31294 ] ], "ids": [ 509, 1082, 1093, 1641, 2965, 3275, 4126, 4835, 5301, 7666, 7980, 8129, 8208, 8477, 10191, 10851, 11470, 15211, 16321, 17796, 19001, 24821, 25066, 25080, 25401, 25790, 25998, 26515, 27144, 27202, 27821, 27885, 28028, 28432, 28659, 29294, 31270, 31294 ] }