Upload tokenizer

special_tokens_map.json

@@ -1,6 +1,31 @@
 {
-  "bos_token": "[BOS]",
-  "eos_token": "[EOS]",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "[MASK]",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -45,8 +45,13 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "[EOS]",
   "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": null,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "tokenizer_class": "PreTrainedTokenizer",
   "unk_token": "[UNK]"
 }