Upload tokenizer

tokenizer_config.json

@@ -34,9 +34,10 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "do_lower_case": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",

vocab.json

@@ -1,46 +1,46 @@
 {
-  "'": 33,
+  "'": 15,
   "[PAD]": 43,
   "[UNK]": 42,
-  "a": 30,
-  "b": 28,
-  "c": 7,
-  "d": 36,
-  "e": 39,
-  "f": 14,
-  "g": 31,
-  "h": 16,
-  "i": 27,
-  "j": 12,
-  "k": 15,
-  "l": 1,
-  "m": 26,
-  "n": 2,
-  "o": 9,
-  "p": 17,
-  "q": 32,
-  "r": 4,
-  "s": 13,
-  "t": 18,
-  "u": 20,
-  "v": 41,
-  "w": 6,
-  "x": 10,
-  "y": 0,
-  "z": 38,
-  "|": 23,
-  "à": 3,
-  "á": 8,
-  "â": 5,
-  "ä": 34,
-  "è": 29,
-  "é": 25,
-  "ê": 19,
-  "ë": 35,
-  "ï": 37,
-  "ó": 22,
-  "ô": 24,
-  "ú": 40,
-  "û": 21,
+  "a": 33,
+  "b": 19,
+  "c": 41,
+  "d": 26,
+  "e": 7,
+  "f": 16,
+  "g": 29,
+  "h": 35,
+  "i": 34,
+  "j": 5,
+  "k": 21,
+  "l": 2,
+  "m": 10,
+  "n": 0,
+  "o": 36,
+  "p": 18,
+  "q": 14,
+  "r": 1,
+  "s": 17,
+  "t": 3,
+  "u": 28,
+  "v": 25,
+  "w": 13,
+  "x": 8,
+  "y": 23,
+  "z": 4,
+  "|": 27,
+  "à": 9,
+  "á": 30,
+  "â": 37,
+  "ä": 6,
+  "è": 40,
+  "é": 20,
+  "ê": 39,
+  "ë": 31,
+  "ï": 38,
+  "ó": 12,
+  "ô": 22,
+  "ú": 24,
+  "û": 32,
   "ü": 11
 }