Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 35,
-  "<s>": 34
+  "</s>": 27,
+  "<s>": 26
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "32": {
+    "24": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "33": {
+    "25": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "34": {
+    "26": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "35": {
+    "27": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,36 +1,28 @@
 {
-  ",": 14,
-  ".": 26,
-  ":": 12,
-  "A": 13,
-  "B": 1,
-  "P": 16,
-  "S": 20,
-  "W": 25,
-  "[PAD]": 33,
-  "[UNK]": 32,
-  "a": 23,
-  "b": 27,
-  "c": 19,
-  "d": 22,
-  "e": 18,
-  "f": 29,
-  "g": 31,
-  "h": 28,
-  "i": 5,
+  " ": 7,
+  "[PAD]": 25,
+  "[UNK]": 24,
+  "a": 17,
+  "b": 19,
+  "c": 14,
+  "d": 15,
+  "e": 13,
+  "f": 21,
+  "g": 23,
+  "h": 20,
+  "i": 4,
   "k": 0,
-  "l": 10,
-  "m": 3,
-  "n": 6,
-  "o": 7,
-  "p": 21,
-  "r": 15,
-  "s": 9,
-  "t": 11,
-  "u": 17,
-  "v": 24,
-  "w": 2,
-  "x": 30,
-  "y": 4,
-  "|": 8
+  "l": 9,
+  "m": 2,
+  "n": 5,
+  "o": 6,
+  "p": 16,
+  "r": 11,
+  "s": 8,
+  "t": 10,
+  "u": 12,
+  "v": 18,
+  "w": 1,
+  "x": 22,
+  "y": 3
 }