Upload tokenizer

tokenizer_config.json

@@ -1,38 +1,4 @@
 {
-  "added_tokens_decoder": {
-    "28": {
-      "content": "[UNK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "29": {
-      "content": "[PAD]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "30": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "31": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,

vocab.json

@@ -2,31 +2,31 @@
   "'": 9,
   "[PAD]": 29,
   "[UNK]": 28,
-  "a": 4,
-  "b": 11,
-  "c": 2,
-  "d": 26,
-  "e": 16,
+  "a": 0,
+  "b": 7,
+  "c": 22,
+  "d": 27,
+  "e": 5,
   "f": 20,
-  "g": 0,
+  "g": 13,
   "h": 14,
-  "i": 15,
-  "j": 8,
-  "k": 22,
-  "l": 19,
-  "m": 23,
-  "n": 27,
-  "o": 13,
-  "p": 3,
-  "q": 10,
-  "r": 7,
-  "s": 6,
-  "t": 17,
+  "i": 8,
+  "j": 24,
+  "k": 21,
+  "l": 15,
+  "m": 3,
+  "n": 23,
+  "o": 26,
+  "p": 4,
+  "q": 11,
+  "r": 16,
+  "s": 17,
+  "t": 19,
   "u": 1,
-  "v": 21,
-  "w": 18,
-  "x": 24,
-  "y": 5,
-  "z": 25,
-  "|": 12
+  "v": 12,
+  "w": 6,
+  "x": 2,
+  "y": 25,
+  "z": 10,
+  "|": 18
 }