Upload tokenizer

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 32,
+  "<s>": 31,
+  "[PAD]": 30,
+  "[UNK]": 29
+}

tokenizer_config.json

@@ -1,4 +1,39 @@
 {
+  "added_tokens_decoder": {
+    "29": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,

vocab.json

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