Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 26,
-  "<s>": 25
+  "</s>": 38,
+  "<s>": 37
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "23": {
+    "35": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "24": {
+    "36": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "25": {
+    "37": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "26": {
+    "38": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -34,7 +34,7 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "do_lower_case": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,

vocab.json

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