Upload tokenizer
Browse files- tokenizer.json +39 -40
- vocab.json +1 -1
tokenizer.json
CHANGED
@@ -326,46 +326,45 @@
|
|
326 |
"ظ": 115,
|
327 |
"ع": 116,
|
328 |
"غ": 117,
|
329 |
-
"
|
330 |
-
"
|
331 |
-
"
|
332 |
-
"
|
333 |
-
"
|
334 |
-
"
|
335 |
-
"
|
336 |
-
"
|
337 |
-
"
|
338 |
-
"
|
339 |
-
"
|
340 |
-
"
|
341 |
-
"
|
342 |
-
"
|
343 |
-
"
|
344 |
-
"
|
345 |
-
"
|
346 |
-
"
|
347 |
-
"
|
348 |
-
"
|
349 |
-
"
|
350 |
-
"
|
351 |
-
"
|
352 |
-
"
|
353 |
-
"
|
354 |
-
"
|
355 |
-
"
|
356 |
-
"
|
357 |
-
"
|
358 |
-
"
|
359 |
-
"
|
360 |
-
"
|
361 |
-
"
|
362 |
-
"
|
363 |
-
"
|
364 |
-
"
|
365 |
-
"
|
366 |
-
"
|
367 |
-
"
|
368 |
-
"�": 157
|
369 |
},
|
370 |
"merges": []
|
371 |
}
|
|
|
326 |
"ظ": 115,
|
327 |
"ع": 116,
|
328 |
"غ": 117,
|
329 |
+
"ف": 118,
|
330 |
+
"ق": 119,
|
331 |
+
"ك": 120,
|
332 |
+
"ل": 121,
|
333 |
+
"م": 122,
|
334 |
+
"ن": 123,
|
335 |
+
"ه": 124,
|
336 |
+
"و": 125,
|
337 |
+
"ى": 126,
|
338 |
+
"ي": 127,
|
339 |
+
"ً": 128,
|
340 |
+
"ٌ": 129,
|
341 |
+
"ٍ": 130,
|
342 |
+
"َ": 131,
|
343 |
+
"ُ": 132,
|
344 |
+
"ِ": 133,
|
345 |
+
"ّ": 134,
|
346 |
+
"ْ": 135,
|
347 |
+
"ٓ": 136,
|
348 |
+
"٤": 137,
|
349 |
+
"٩": 138,
|
350 |
+
"ٹ": 139,
|
351 |
+
"ک": 140,
|
352 |
+
"ی": 141,
|
353 |
+
"": 142,
|
354 |
+
"": 143,
|
355 |
+
"": 144,
|
356 |
+
"–": 145,
|
357 |
+
"“": 146,
|
358 |
+
"”": 147,
|
359 |
+
"„": 148,
|
360 |
+
"†": 149,
|
361 |
+
"…": 150,
|
362 |
+
"": 151,
|
363 |
+
"": 152,
|
364 |
+
"": 153,
|
365 |
+
"": 154,
|
366 |
+
"ﺑ": 155,
|
367 |
+
"�": 156
|
|
|
368 |
},
|
369 |
"merges": []
|
370 |
}
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"<|endoftext|>":0,"<|vsep|>":1,"<|bsep|>":2,"<|pad|>":3,"<|psep|>":4,"<|meter_0|>":5,"<|meter_1|>":6,"<|meter_2|>":7,"<|meter_3|>":8,"<|meter_4|>":9,"<|meter_5|>":10,"<|meter_6|>":11,"<|meter_7|>":12,"<|meter_8|>":13,"<|meter_9|>":14,"<|meter_10|>":15,"<|meter_11|>":16,"<|meter_12|>":17,"<|meter_13|>":18,"<|meter_14|>":19,"<|meter_15|>":20,"\t":21," ":22,"!":23,"\"":24,"#":25,"(":26,")":27,"*":28,",":29,"-":30,".":31,"/":32,"0":33,"1":34,"2":35,"3":36,"4":37,"5":38,"6":39,"7":40,"8":41,"9":42,":":43,";":44,"<":45,"=":46,">":47,"?":48,"G":49,"H":50,"I":51,"P":52,"R":53,"T":54,"[":55,"]":56,"_":57,"a":58,"b":59,"c":60,"e":61,"f":62,"g":63,"h":64,"i":65,"l":66,"m":67,"n":68,"p":69,"r":70,"s":71,"t":72,"v":73,"x":74,"y":75,"|":76,"}":77,"~":78," ":79,"£":80,"§":81,"«":82,"±":83,"´":84,"·":85,"»":86,"×":87,"ˆ":88,"،":89,"؛":90,"؟":91,"ء":92,"آ":93,"أ":94,"ؤ":95,"إ":96,"ئ":97,"ا":98,"ب":99,"ة":100,"ت":101,"ث":102,"ج":103,"ح":104,"خ":105,"د":106,"ذ":107,"ر":108,"ز":109,"س":110,"ش":111,"ص":112,"ض":113,"ط":114,"ظ":115,"ع":116,"غ":117,"
|
|
|
1 |
+
{"<|endoftext|>":0,"<|vsep|>":1,"<|bsep|>":2,"<|pad|>":3,"<|psep|>":4,"<|meter_0|>":5,"<|meter_1|>":6,"<|meter_2|>":7,"<|meter_3|>":8,"<|meter_4|>":9,"<|meter_5|>":10,"<|meter_6|>":11,"<|meter_7|>":12,"<|meter_8|>":13,"<|meter_9|>":14,"<|meter_10|>":15,"<|meter_11|>":16,"<|meter_12|>":17,"<|meter_13|>":18,"<|meter_14|>":19,"<|meter_15|>":20,"\t":21," ":22,"!":23,"\"":24,"#":25,"(":26,")":27,"*":28,",":29,"-":30,".":31,"/":32,"0":33,"1":34,"2":35,"3":36,"4":37,"5":38,"6":39,"7":40,"8":41,"9":42,":":43,";":44,"<":45,"=":46,">":47,"?":48,"G":49,"H":50,"I":51,"P":52,"R":53,"T":54,"[":55,"]":56,"_":57,"a":58,"b":59,"c":60,"e":61,"f":62,"g":63,"h":64,"i":65,"l":66,"m":67,"n":68,"p":69,"r":70,"s":71,"t":72,"v":73,"x":74,"y":75,"|":76,"}":77,"~":78," ":79,"£":80,"§":81,"«":82,"±":83,"´":84,"·":85,"»":86,"×":87,"ˆ":88,"،":89,"؛":90,"؟":91,"ء":92,"آ":93,"أ":94,"ؤ":95,"إ":96,"ئ":97,"ا":98,"ب":99,"ة":100,"ت":101,"ث":102,"ج":103,"ح":104,"خ":105,"د":106,"ذ":107,"ر":108,"ز":109,"س":110,"ش":111,"ص":112,"ض":113,"ط":114,"ظ":115,"ع":116,"غ":117,"ف":118,"ق":119,"ك":120,"ل":121,"م":122,"ن":123,"ه":124,"و":125,"ى":126,"ي":127,"ً":128,"ٌ":129,"ٍ":130,"َ":131,"ُ":132,"ِ":133,"ّ":134,"ْ":135,"ٓ":136,"٤":137,"٩":138,"ٹ":139,"ک":140,"ی":141,"":142,"":143,"":144,"–":145,"“":146,"”":147,"„":148,"†":149,"…":150,"":151,"":152,"":153,"":154,"ﺑ":155,"�":156}
|