Skip to content

Instantly share code, notes, and snippets.

@cccntu
Created October 1, 2021 15:38
Show Gist options
  • Save cccntu/a644090cafd7abdeb0a56367df1ee930 to your computer and use it in GitHub Desktop.
Save cccntu/a644090cafd7abdeb0a56367df1ee930 to your computer and use it in GitHub Desktop.
tokens that are numbers in gpt2 tokenizer
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("gpt2")
# model = AutoModelWithLMHead.from_pretrained("gpt2")
import re
nums = []
for t in tokenizer.vocab:
if re.match('[0-9]', t):
nums.append((int(t),t))
# break
len(sorted(nums)),sorted(nums)
(994,
[(0, '0'),
(0, '00'),
(0, '000'),
(0, '0000'),
(0, '00000'),
(0, '000000'),
(0, '0000000'),
(0, '00000000'),
(0, '0000000000000000'),
(1, '0001'),
(1, '001'),
(1, '01'),
(1, '1'),
(2, '0002'),
(2, '002'),
(2, '02'),
(2, '2'),
(3, '003'),
(3, '03'),
(3, '3'),
(4, '004'),
(4, '04'),
(4, '4'),
(5, '005'),
(5, '05'),
(5, '5'),
(6, '006'),
(6, '06'),
(6, '6'),
(7, '00007'),
(7, '007'),
(7, '07'),
(7, '7'),
(8, '008'),
(8, '08'),
(8, '8'),
(9, '009'),
(9, '09'),
(9, '9'),
(10, '0010'),
(10, '010'),
(10, '10'),
(11, '011'),
(11, '11'),
(12, '012'),
(12, '12'),
(13, '013'),
(13, '13'),
(14, '014'),
(14, '14'),
(15, '015'),
(15, '15'),
(16, '016'),
(16, '16'),
(17, '017'),
(17, '17'),
(18, '018'),
(18, '18'),
(19, '019'),
(19, '19'),
(20, '020'),
(20, '20'),
(21, '021'),
(21, '21'),
(22, '022'),
(22, '22'),
(23, '023'),
(23, '23'),
(24, '024'),
(24, '24'),
(25, '025'),
(25, '25'),
(26, '026'),
(26, '26'),
(27, '027'),
(27, '27'),
(28, '028'),
(28, '28'),
(29, '029'),
(29, '29'),
(30, '030'),
(30, '30'),
(31, '031'),
(31, '31'),
(32, '032'),
(32, '32'),
(33, '033'),
(33, '33'),
(34, '034'),
(34, '34'),
(35, '035'),
(35, '35'),
(36, '036'),
(36, '36'),
(37, '37'),
(38, '38'),
(39, '39'),
(40, '040'),
(40, '40'),
(41, '041'),
(41, '41'),
(42, '42'),
(43, '043'),
(43, '43'),
(44, '044'),
(44, '44'),
(45, '045'),
(45, '45'),
(46, '046'),
(46, '46'),
(47, '047'),
(47, '47'),
(48, '048'),
(48, '48'),
(49, '49'),
(50, '050'),
(50, '50'),
(51, '51'),
(52, '052'),
(52, '52'),
(53, '53'),
(54, '54'),
(55, '055'),
(55, '55'),
(56, '56'),
(57, '057'),
(57, '57'),
(58, '58'),
(59, '059'),
(59, '59'),
(60, '060'),
(60, '60'),
(61, '61'),
(62, '62'),
(63, '63'),
(64, '64'),
(65, '65'),
(66, '66'),
(67, '67'),
(68, '68'),
(69, '69'),
(70, '070'),
(70, '70'),
(71, '71'),
(72, '72'),
(73, '73'),
(74, '74'),
(75, '075'),
(75, '75'),
(76, '76'),
(77, '77'),
(78, '78'),
(79, '79'),
(80, '080'),
(80, '80'),
(81, '81'),
(82, '82'),
(83, '083'),
(83, '83'),
(84, '84'),
(85, '85'),
(86, '86'),
(87, '87'),
(88, '088'),
(88, '88'),
(89, '089'),
(89, '89'),
(90, '090'),
(90, '90'),
(91, '91'),
(92, '92'),
(93, '93'),
(94, '94'),
(95, '95'),
(96, '96'),
(97, '97'),
(98, '98'),
(99, '99'),
(100, '0100'),
(100, '100'),
(101, '101'),
(102, '102'),
(103, '103'),
(104, '104'),
(105, '105'),
(106, '106'),
(107, '107'),
(108, '108'),
(109, '109'),
(110, '110'),
(111, '111'),
(112, '112'),
(113, '113'),
(114, '114'),
(115, '115'),
(116, '116'),
(117, '117'),
(118, '118'),
(119, '119'),
(120, '120'),
(121, '121'),
(122, '122'),
(123, '123'),
(124, '124'),
(125, '125'),
(126, '126'),
(127, '127'),
(128, '128'),
(129, '129'),
(130, '130'),
(131, '131'),
(132, '132'),
(133, '133'),
(134, '134'),
(135, '135'),
(136, '136'),
(137, '137'),
(138, '138'),
(139, '139'),
(140, '140'),
(141, '141'),
(142, '142'),
(143, '143'),
(144, '144'),
(145, '145'),
(146, '146'),
(147, '147'),
(148, '148'),
(149, '149'),
(150, '150'),
(151, '151'),
(152, '152'),
(153, '153'),
(154, '154'),
(155, '155'),
(156, '156'),
(157, '157'),
(158, '158'),
(159, '159'),
(160, '160'),
(161, '161'),
(162, '162'),
(163, '163'),
(164, '164'),
(165, '165'),
(166, '166'),
(167, '167'),
(168, '168'),
(169, '169'),
(170, '170'),
(171, '171'),
(172, '172'),
(173, '173'),
(174, '174'),
(175, '175'),
(176, '176'),
(177, '177'),
(178, '178'),
(179, '179'),
(180, '180'),
(181, '181'),
(182, '182'),
(183, '183'),
(184, '184'),
(185, '185'),
(186, '186'),
(187, '187'),
(188, '188'),
(189, '189'),
(190, '190'),
(191, '191'),
(192, '192'),
(193, '193'),
(194, '194'),
(195, '195'),
(196, '196'),
(197, '197'),
(198, '198'),
(199, '199'),
(200, '0200'),
(200, '200'),
(201, '201'),
(202, '202'),
(203, '203'),
(204, '204'),
(205, '205'),
(206, '206'),
(207, '207'),
(208, '208'),
(209, '209'),
(210, '210'),
(211, '211'),
(212, '212'),
(213, '213'),
(214, '214'),
(215, '215'),
(216, '216'),
(217, '217'),
(218, '218'),
(219, '219'),
(220, '220'),
(221, '221'),
(222, '222'),
(223, '223'),
(224, '224'),
(225, '225'),
(226, '226'),
(227, '227'),
(228, '228'),
(229, '229'),
(230, '230'),
(231, '231'),
(232, '232'),
(233, '233'),
(234, '234'),
(235, '235'),
(236, '236'),
(237, '237'),
(238, '238'),
(239, '239'),
(240, '240'),
(241, '241'),
(242, '242'),
(243, '243'),
(244, '244'),
(245, '245'),
(246, '246'),
(247, '247'),
(248, '248'),
(249, '249'),
(250, '250'),
(251, '251'),
(252, '252'),
(253, '253'),
(254, '254'),
(255, '255'),
(256, '256'),
(257, '257'),
(258, '258'),
(259, '259'),
(260, '260'),
(261, '261'),
(262, '262'),
(263, '263'),
(264, '264'),
(265, '265'),
(266, '266'),
(267, '267'),
(268, '268'),
(269, '269'),
(270, '270'),
(271, '271'),
(272, '272'),
(273, '273'),
(274, '274'),
(275, '275'),
(276, '276'),
(277, '277'),
(278, '278'),
(279, '279'),
(280, '280'),
(281, '281'),
(282, '282'),
(283, '283'),
(284, '284'),
(285, '285'),
(286, '286'),
(287, '287'),
(288, '288'),
(289, '289'),
(290, '290'),
(291, '291'),
(292, '292'),
(293, '293'),
(294, '294'),
(295, '295'),
(296, '296'),
(297, '297'),
(298, '298'),
(299, '299'),
(300, '300'),
(301, '301'),
(302, '302'),
(303, '303'),
(304, '304'),
(305, '305'),
(306, '306'),
(307, '307'),
(308, '308'),
(309, '309'),
(310, '310'),
(311, '311'),
(312, '312'),
(313, '313'),
(314, '314'),
(315, '315'),
(316, '316'),
(317, '317'),
(318, '318'),
(319, '319'),
(320, '320'),
(321, '321'),
(322, '322'),
(323, '323'),
(324, '324'),
(325, '325'),
(326, '326'),
(327, '327'),
(328, '328'),
(329, '329'),
(330, '330'),
(331, '331'),
(332, '332'),
(333, '333'),
(334, '334'),
(335, '335'),
(336, '336'),
(337, '337'),
(338, '338'),
(339, '339'),
(340, '340'),
(341, '341'),
(342, '342'),
(343, '343'),
(344, '344'),
(345, '345'),
(346, '346'),
(347, '347'),
(348, '348'),
(349, '349'),
(350, '350'),
(351, '351'),
(352, '352'),
(353, '353'),
(354, '354'),
(355, '355'),
(356, '356'),
(357, '357'),
(358, '358'),
(359, '359'),
(360, '360'),
(361, '361'),
(362, '362'),
(363, '363'),
(364, '364'),
(365, '365'),
(366, '366'),
(367, '367'),
(368, '368'),
(369, '369'),
(370, '370'),
(371, '371'),
(372, '372'),
(373, '373'),
(374, '374'),
(375, '375'),
(376, '376'),
(377, '377'),
(378, '378'),
(379, '379'),
(380, '380'),
(381, '381'),
(382, '382'),
(383, '383'),
(384, '384'),
(385, '385'),
(386, '386'),
(387, '387'),
(388, '388'),
(389, '389'),
(390, '390'),
(391, '391'),
(392, '392'),
(393, '393'),
(394, '394'),
(395, '395'),
(396, '396'),
(397, '397'),
(398, '398'),
(399, '399'),
(400, '400'),
(401, '401'),
(402, '402'),
(403, '403'),
(404, '404'),
(405, '405'),
(406, '406'),
(407, '407'),
(408, '408'),
(409, '409'),
(410, '410'),
(411, '411'),
(412, '412'),
(413, '413'),
(414, '414'),
(415, '415'),
(416, '416'),
(417, '417'),
(418, '418'),
(419, '419'),
(420, '420'),
(421, '421'),
(422, '422'),
(423, '423'),
(424, '424'),
(425, '425'),
(426, '426'),
(427, '427'),
(428, '428'),
(429, '429'),
(430, '430'),
(431, '431'),
(432, '432'),
(433, '433'),
(434, '434'),
(435, '435'),
(436, '436'),
(437, '437'),
(438, '438'),
(439, '439'),
(440, '440'),
(441, '441'),
(442, '442'),
(443, '443'),
(444, '444'),
(445, '445'),
(446, '446'),
(447, '447'),
(448, '448'),
(449, '449'),
(450, '450'),
(451, '451'),
(452, '452'),
(453, '453'),
(454, '454'),
(455, '455'),
(456, '456'),
(457, '457'),
(458, '458'),
(459, '459'),
(460, '460'),
(461, '461'),
(462, '462'),
(463, '463'),
(464, '464'),
(465, '465'),
(466, '466'),
(467, '467'),
(468, '468'),
(469, '469'),
(470, '470'),
(471, '471'),
(472, '472'),
(473, '473'),
(474, '474'),
(475, '475'),
(476, '476'),
(477, '477'),
(478, '478'),
(479, '479'),
(480, '480'),
(481, '481'),
(482, '482'),
(483, '483'),
(484, '484'),
(485, '485'),
(486, '486'),
(487, '487'),
(488, '488'),
(489, '489'),
(490, '490'),
(491, '491'),
(492, '492'),
(493, '493'),
(494, '494'),
(495, '495'),
(496, '496'),
(497, '497'),
(498, '498'),
(499, '499'),
(500, '500'),
(501, '501'),
(502, '502'),
(503, '503'),
(504, '504'),
(505, '505'),
(506, '506'),
(507, '507'),
(508, '508'),
(509, '509'),
(510, '510'),
(511, '511'),
(512, '512'),
(513, '513'),
(514, '514'),
(515, '515'),
(516, '516'),
(517, '517'),
(518, '518'),
(519, '519'),
(520, '520'),
(522, '522'),
(523, '523'),
(524, '524'),
(525, '525'),
(526, '526'),
(528, '528'),
(529, '529'),
(530, '530'),
(533, '533'),
(535, '535'),
(536, '536'),
(537, '537'),
(538, '538'),
(540, '540'),
(544, '544'),
(545, '545'),
(546, '546'),
(548, '548'),
(549, '549'),
(550, '550'),
(551, '551'),
(552, '552'),
(553, '553'),
(554, '554'),
(555, '555'),
(556, '556'),
(557, '557'),
(558, '558'),
(559, '559'),
(560, '560'),
(561, '561'),
(562, '562'),
(563, '563'),
(565, '565'),
(568, '568'),
(570, '570'),
(571, '571'),
(572, '572'),
(573, '573'),
(574, '574'),
(575, '575'),
(576, '576'),
(577, '577'),
(578, '578'),
(579, '579'),
(580, '580'),
(581, '581'),
(582, '582'),
(583, '583'),
(584, '584'),
(585, '585'),
(586, '586'),
(587, '587'),
(588, '588'),
(589, '589'),
(590, '590'),
(591, '591'),
(592, '592'),
(593, '593'),
(594, '594'),
(595, '595'),
(596, '596'),
(597, '597'),
(598, '598'),
(599, '599'),
(600, '600'),
(601, '601'),
(602, '602'),
(603, '603'),
(604, '604'),
(605, '605'),
(606, '606'),
(607, '607'),
(608, '608'),
(609, '609'),
(610, '610'),
(612, '612'),
(613, '613'),
(614, '614'),
(615, '615'),
(616, '616'),
(617, '617'),
(618, '618'),
(620, '620'),
(623, '623'),
(625, '625'),
(626, '626'),
(627, '627'),
(628, '628'),
(629, '629'),
(630, '630'),
(635, '635'),
(640, '640'),
(641, '641'),
(642, '642'),
(643, '643'),
(644, '644'),
(645, '645'),
(646, '646'),
(647, '647'),
(648, '648'),
(649, '649'),
(650, '650'),
(651, '651'),
(652, '652'),
(653, '653'),
(654, '654'),
(655, '655'),
(656, '656'),
(657, '657'),
(658, '658'),
(659, '659'),
(660, '660'),
(661, '661'),
(662, '662'),
(663, '663'),
(665, '665'),
(666, '666'),
(667, '667'),
(668, '668'),
(669, '669'),
(670, '670'),
(671, '671'),
(672, '672'),
(673, '673'),
(674, '674'),
(675, '675'),
(676, '676'),
(677, '677'),
(678, '678'),
(679, '679'),
(680, '680'),
(681, '681'),
(682, '682'),
(683, '683'),
(684, '684'),
(685, '685'),
(686, '686'),
(687, '687'),
(688, '688'),
(689, '689'),
(690, '690'),
(691, '691'),
(692, '692'),
(693, '693'),
(694, '694'),
(695, '695'),
(696, '696'),
(697, '697'),
(698, '698'),
(699, '699'),
(700, '700'),
(701, '701'),
(702, '702'),
(703, '703'),
(704, '704'),
(705, '705'),
(706, '706'),
(707, '707'),
(708, '708'),
(709, '709'),
(710, '710'),
(712, '712'),
(713, '713'),
(714, '714'),
(718, '718'),
(720, '720'),
(725, '725'),
(727, '727'),
(728, '728'),
(729, '729'),
(730, '730'),
(733, '733'),
(736, '736'),
(740, '740'),
(745, '745'),
(747, '747'),
(748, '748'),
(750, '750'),
(751, '751'),
(752, '752'),
(753, '753'),
(754, '754'),
(755, '755'),
(756, '756'),
(757, '757'),
(758, '758'),
(759, '759'),
(760, '760'),
(762, '762'),
(763, '763'),
(765, '765'),
(767, '767'),
(768, '768'),
(770, '770'),
(771, '771'),
(772, '772'),
(773, '773'),
(774, '774'),
(775, '775'),
(776, '776'),
(777, '777'),
(778, '778'),
(779, '779'),
(780, '780'),
(781, '781'),
(782, '782'),
(783, '783'),
(784, '784'),
(785, '785'),
(786, '786'),
(787, '787'),
(789, '789'),
(790, '790'),
(792, '792'),
(793, '793'),
(794, '794'),
(795, '795'),
(796, '796'),
(797, '797'),
(798, '798'),
(799, '799'),
(800, '800'),
(801, '801'),
(802, '802'),
(803, '803'),
(804, '804'),
(805, '805'),
(806, '806'),
(807, '807'),
(808, '808'),
(809, '809'),
(810, '810'),
(815, '815'),
(820, '820'),
(825, '825'),
(830, '830'),
(833, '833'),
(840, '840'),
(850, '850'),
(855, '855'),
(860, '860'),
(864, '864'),
(866, '866'),
(870, '870'),
(875, '875'),
(877, '877'),
(880, '880'),
(882, '882'),
(883, '883'),
(884, '884'),
(885, '885'),
(886, '886'),
(887, '887'),
(888, '888'),
(889, '889'),
(893, '893'),
(896, '896'),
(899, '899'),
(900, '900'),
(901, '901'),
(905, '905'),
(909, '909'),
(910, '910'),
(911, '911'),
(915, '915'),
(916, '916'),
(920, '920'),
(925, '925'),
(930, '930'),
(940, '940'),
(949, '949'),
(950, '950'),
(951, '951'),
(952, '952'),
(953, '953'),
(954, '954'),
(956, '956'),
(960, '960'),
(968, '968'),
(969, '969'),
(970, '970'),
(975, '975'),
(978, '978'),
(980, '980'),
(985, '985'),
(986, '986'),
(987, '987'),
(989, '989'),
(990, '990'),
(992, '992'),
(993, '993'),
(994, '994'),
(995, '995'),
(996, '996'),
(997, '997'),
(998, '998'),
(999, '999'),
(1000, '1000'),
(1001, '1001'),
(1007, '1007'),
(1016, '1016'),
(1024, '1024'),
(1027, '1027'),
(1080, '1080'),
(1100, '1100'),
(1111, '1111'),
(1200, '1200'),
(1500, '1500'),
(1600, '1600'),
(1800, '1800'),
(1900, '1900'),
(1920, '1920'),
(1945, '1945'),
(1950, '1950'),
(1959, '1959'),
(1960, '1960'),
(1963, '1963'),
(1964, '1964'),
(1965, '1965'),
(1966, '1966'),
(1967, '1967'),
(1968, '1968'),
(1969, '1969'),
(1970, '1970'),
(1971, '1971'),
(1972, '1972'),
(1973, '1973'),
(1974, '1974'),
(1975, '1975'),
(1976, '1976'),
(1977, '1977'),
(1978, '1978'),
(1979, '1979'),
(1980, '1980'),
(1981, '1981'),
(1982, '1982'),
(1983, '1983'),
(1984, '1984'),
(1985, '1985'),
(1986, '1986'),
(1987, '1987'),
(1988, '1988'),
(1989, '1989'),
(1990, '1990'),
(1991, '1991'),
(1992, '1992'),
(1993, '1993'),
(1994, '1994'),
(1995, '1995'),
(1996, '1996'),
(1997, '1997'),
(1998, '1998'),
(1999, '1999'),
(2000, '2000'),
(2001, '2001'),
(2002, '2002'),
(2003, '2003'),
(2004, '2004'),
(2005, '2005'),
(2006, '2006'),
(2007, '2007'),
(2008, '2008'),
(2009, '2009'),
(2010, '2010'),
(2011, '2011'),
(2012, '2012'),
(2013, '2013'),
(2014, '2014'),
(2015, '2015'),
(2016, '2016'),
(2017, '2017'),
(2018, '2018'),
(2019, '2019'),
(2020, '2020'),
(2200, '2200'),
(2500, '2500'),
(3000, '3000'),
(3333, '3333'),
(4000, '4000'),
(5000, '5000'),
(6000, '6000'),
(6666, '6666'),
(7601, '7601'),
(8000, '8000'),
(9999, '9999'),
(10000, '10000'),
(20439, '20439'),
(70710, '70710'),
(76561, '76561'),
(200000, '00200000'),
(200000, '200000'),
(66666666, '66666666')])
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment