Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 37,
-  "<s>": 36
+  "</s>": 56,
+  "<s>": 55
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "34": {
+    "53": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "35": {
+    "54": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "36": {
+    "55": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "37": {
+    "56": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,38 +1,57 @@
 {
-  "[PAD]": 35,
-  "[UNK]": 34,
+  "[PAD]": 54,
+  "[UNK]": 53,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "e": 4,
+  "f": 5,
+  "g": 6,
+  "h": 7,
+  "i": 8,
+  "k": 9,
+  "l": 10,
+  "m": 11,
+  "n": 12,
+  "o": 13,
+  "p": 14,
+  "r": 15,
+  "s": 16,
+  "t": 17,
+  "x": 18,
+  "z": 19,
   "|": 0,
-  "а": 1,
-  "б": 2,
-  "в": 3,
-  "г": 4,
-  "д": 5,
-  "е": 6,
-  "ж": 7,
-  "з": 8,
-  "и": 9,
-  "й": 10,
-  "к": 11,
-  "л": 12,
-  "м": 13,
-  "н": 14,
-  "о": 15,
-  "п": 16,
-  "р": 17,
-  "с": 18,
-  "т": 19,
-  "у": 20,
-  "ф": 21,
-  "х": 22,
-  "ц": 23,
-  "ч": 24,
-  "ш": 25,
-  "щ": 26,
-  "ъ": 27,
-  "ы": 28,
-  "ь": 29,
-  "э": 30,
-  "ю": 31,
-  "я": 32,
-  "ё": 33
+  "а": 20,
+  "б": 21,
+  "в": 22,
+  "г": 23,
+  "д": 24,
+  "е": 25,
+  "ж": 26,
+  "з": 27,
+  "и": 28,
+  "й": 29,
+  "к": 30,
+  "л": 31,
+  "м": 32,
+  "н": 33,
+  "о": 34,
+  "п": 35,
+  "р": 36,
+  "с": 37,
+  "т": 38,
+  "у": 39,
+  "ф": 40,
+  "х": 41,
+  "ц": 42,
+  "ч": 43,
+  "ш": 44,
+  "щ": 45,
+  "ъ": 46,
+  "ы": 47,
+  "ь": 48,
+  "э": 49,
+  "ю": 50,
+  "я": 51,
+  "ё": 52
 }