mms-zeroshot / utils /punctuations.lst
Vineel Pratap
autolm
6f27821
raw
history blame contribute delete
No virus
6.07 kB
 7355 INVALID UNICODE 0x81
 5265 INVALID UNICODE 0x90
 75 INVALID UNICODE 0x8
 31 INVALID UNICODE 0x8d
” 3 INVALID UNICODE 0x94
 2 INVALID UNICODE 0x8f
 2 INVALID UNICODE 0x1a
 1 INVALID UNICODE 0x9d
“ 1 INVALID UNICODE 0x93
’ 1 INVALID UNICODE 0x92
8647 INVALID UNICODE 0xe295
6650 INVALID UNICODE 0xf21d
6234 INVALID UNICODE 0xf62d
4815 INVALID UNICODE 0xf173
4789 INVALID UNICODE 0xe514
4409 INVALID UNICODE 0xe293
3881 INVALID UNICODE 0xf523
3788 INVALID UNICODE 0xe233
2448 INVALID UNICODE 0xf50f
2177 INVALID UNICODE 0xe232
1955 INVALID UNICODE 0xea7b
1926 INVALID UNICODE 0xf172
973 INVALID UNICODE 0xe290
972 INVALID UNICODE 0xf519
661 INVALID UNICODE 0xe292
591 INVALID UNICODE 0xe328
509 INVALID UNICODE 0xe2fa
458 INVALID UNICODE 0xe234
446 INVALID UNICODE 0xe043
419 INVALID UNICODE 0xe040
399 INVALID UNICODE 0xe2fb
387 INVALID UNICODE 0xe32b
381 INVALID UNICODE 0xe236
374 INVALID UNICODE 0xf511
314 INVALID UNICODE 0xe517
296 INVALID UNICODE 0xe2fe
293 INVALID UNICODE 0xe492
291 INVALID UNICODE 0xf52d
289 INVALID UNICODE 0xe2fc
195 INVALID UNICODE 0xf521
190 INVALID UNICODE 0xe516
182 INVALID UNICODE 0xe041
178 INVALID UNICODE 0xf529
113 INVALID UNICODE 0xe2f9
87 INVALID UNICODE 0xe2d9
78 INVALID UNICODE 0xe32a
76 INVALID UNICODE 0xe291
74 INVALID UNICODE 0xe296
66 INVALID UNICODE 0xe518
52 INVALID UNICODE 0xe32c
46 INVALID UNICODE 0xe2db
41 INVALID UNICODE 0xe231
34 INVALID UNICODE 0xf522
33 INVALID UNICODE 0xf518
32 INVALID UNICODE 0xf513
27 INVALID UNICODE 0xe32d
25 INVALID UNICODE 0xe32e
23 INVALID UNICODE 0xe06b
15 INVALID UNICODE 0xea01
12 INVALID UNICODE 0xe294
11 INVALID UNICODE 0xe203
8 INVALID UNICODE 0xf218
7 INVALID UNICODE 0xe070
7 INVALID UNICODE 0xe013
5 INVALID UNICODE 0xe2de
4 INVALID UNICODE 0xe493
3 INVALID UNICODE 0xf7e8
3 INVALID UNICODE 0xf7d0
3 INVALID UNICODE 0xe313
2 INVALID UNICODE 0xe329
2 INVALID UNICODE 0xe06d
2 INVALID UNICODE 0xe003
1 INVALID UNICODE 0xf50e
1 INVALID UNICODE 0xf171
1 INVALID UNICODE 0xe01d
71 NOMINAL DIGIT SHAPES 0x206f
3 WORD JOINER 0x2060
126545 HORIZONTAL BAR 0x2015
־ 1028 HEBREW PUNCTUATION MAQAF 0x5be
) 98429 RIGHT PARENTHESIS 0x29
] 27108 RIGHT SQUARE BRACKET 0x5d
1567 RIGHT FLOOR 0x230b
97 RIGHT TORTOISE SHELL BRACKET 0x3015
36 RIGHT BLACK LENTICULAR BRACKET 0x3011
14 ORNATE LEFT PARENTHESIS 0xfd3e
& 170517 AMPERSAND 0x26
106330 TIBETAN MARK SHAD 0xf0d
90203 ETHIOPIC FULL STOP 0x1362
60484 ETHIOPIC COLON 0x1365
60464 TIBETAN MARK DELIMITER TSHEG BSTAR 0xf0c
51567 MYANMAR SIGN SECTION 0x104b
/ 46929 SOLIDUS 0x2f
38042 MYANMAR SIGN LITTLE SECTION 0x104a
· 37985 MIDDLE DOT 0xb7
36310 CARET 0x2038
* 34793 ASTERISK 0x2a
۔ 32432 ARABIC FULL STOP 0x6d4
31906 ETHIOPIC SEMICOLON 0x1364
21519 MYANMAR SYMBOL GENITIVE 0x104f
20834 KHMER SIGN KHAN 0x17d4
15773 LISU PUNCTUATION COMMA 0xa4fe
13473 CANADIAN SYLLABICS FULL STOP 0x166e
12892 KAYAH LI SIGN SHYA 0xa92f
11478 TIFINAGH SEPARATOR MARK 0x2d70
11118 LISU PUNCTUATION FULL STOP 0xa4ff
10763 DEVANAGARI DOUBLE DANDA 0x965
؞ 10403 ARABIC TRIPLE DOT PUNCTUATION MARK 0x61e
8936 MYANMAR SYMBOL COMPLETED 0x104d
· 8431 GREEK ANO TELEIA 0x387
7477 DAGGER 0x2020
6632 MYANMAR SYMBOL LOCATIVE 0x104c
5719 ETHIOPIC COMMA 0x1363
5528 KHMER SIGN CAMNUC PII KUUH 0x17d6
4791 KAYAH LI SIGN CWI 0xa92e
3439 REFERENCE MARK 0x203b
2727 ETHIOPIC PREFACE COLON 0x1366
1749 BULLET 0x2022
1507 PILCROW SIGN 0xb6
1386 MYANMAR SYMBOL AFOREMENTIONED 0x104e
1224 SMALL QUESTION MARK 0xfe56
; 975 GREEK QUESTION MARK 0x37e
827 HORIZONTAL ELLIPSIS 0x2026
% 617 PERCENT SIGN 0x25
468 KATAKANA MIDDLE DOT 0x30fb
306 TIBETAN MARK NYIS SHAD 0xf0e
140 DOUBLE DAGGER 0x2021
# 137 NUMBER SIGN 0x23
@ 125 COMMERCIAL AT 0x40
121 ETHIOPIC WORDSPACE 0x1361
55 KHMER SIGN KOOMUUT 0x17da
49 KHMER SIGN BARIYOOSAN 0x17d5
10 SMALL COMMA 0xfe50
6 TIBETAN MARK CLOSING YIG MGO SGAB MA 0xf05
6 TIBETAN MARK INITIAL YIG MGO MDUN MA 0xf04
2 FULLWIDTH FULL STOP 0xff0e
2 SMALL EXCLAMATION MARK 0xfe57
2 SMALL COLON 0xfe55
2 PER MILLE SIGN 0x2030
1 HALFWIDTH KATAKANA MIDDLE DOT 0xff65
( 98504 LEFT PARENTHESIS 0x28
[ 27245 LEFT SQUARE BRACKET 0x5b
1567 LEFT FLOOR 0x230a
95 LEFT TORTOISE SHELL BRACKET 0x3014
36 LEFT BLACK LENTICULAR BRACKET 0x3010
﴿ 14 ORNATE RIGHT PARENTHESIS 0xfd3f
_ 4851 LOW LINE 0x5f
$ 72 DOLLAR SIGN 0x24
14 EURO SIGN 0x20ac
£ 2 POUND SIGN 0xa3
~ 27462 TILDE 0x7e
= 11450 EQUALS SIGN 0x3d
| 8430 VERTICAL LINE 0x7c
3971 MINUS SIGN 0x2212
1904 MUCH GREATER-THAN 0x226b
1903 MUCH LESS-THAN 0x226a
+ 1450 PLUS SIGN 0x2b
345 FULLWIDTH LESS-THAN SIGN 0xff1c
344 FULLWIDTH GREATER-THAN SIGN 0xff1e
¬ 5 NOT SIGN 0xac
× 4 MULTIPLICATION SIGN 0xd7
2 RIGHTWARDS ARROW 0x2192
537 CANADIAN SYLLABICS CHI SIGN 0x166d
° 499 DEGREE SIGN 0xb0
421 MYANMAR SYMBOL SHAN EXCLAMATION 0x109f
192 REPLACEMENT CHARACTER 0xfffd
54 BOTTOM RIGHT CORNER 0x231f
54 BOTTOM LEFT CORNER 0x231e
© 2 COPYRIGHT SIGN 0xa9
40 NARROW NO-BREAK SPACE 0x202f
1 SIX-PER-EM SPACE 0x2006
˜ 40261 SMALL TILDE 0x2dc
^ 6469 CIRCUMFLEX ACCENT 0x5e
¯ 20 MACRON 0xaf
ˇ 191442 CARON 0x2c7
38144 SUPERSCRIPT LATIN SMALL LETTER N 0x207f
ـ 9440 ARABIC TATWEEL 0x640
6766 THAI CHARACTER MAIYAMOK 0xe46
3310 KHMER SIGN LEK TOO 0x17d7
678 IDEOGRAPHIC ITERATION MARK 0x3005
430 LAO KO LA 0xec6
319 KATAKANA-HIRAGANA PROLONGED SOUND MARK 0x30fc
137 SUPERSCRIPT LATIN SMALL LETTER I 0x2071
11056 BENGALI CURRENCY NUMERATOR FOUR 0x9f7
26 VULGAR FRACTION ONE THIRD 0x2153
½ 26 VULGAR FRACTION ONE HALF 0xbd
¼ 4 VULGAR FRACTION ONE QUARTER 0xbc
1 FRACTION NUMERATOR ONE 0x215f
57 FRACTION SLASH 0x2044