Upload tokenizer files

id2csp_feature.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf54f0b425d9040877d72a5c1b4c5ec93bb9f64b3ca8ad9dcfcc014acdd0960
-size 33699822
+oid sha256:2c8c714a8aead7afcac70003f45428b7f9d405bc4caee937b27c7d8f5516de77
+size 33695410

tokenizer.json

@@ -4,7 +4,7 @@
   "padding": null,
   "added_tokens": [
     {
-      "id": 0,
+      "id": 8284,
       "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
@@ -13,13 +13,22 @@
       "special": true
     },
     {
-      "id": 1,
+      "id": 8285,
       "content": "[UNK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 8286,
+      "content": "[MASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -1 +1 @@
-{"model": "wordlevel", "vocab_size": 8286, "unk_token": "[UNK]", "special_tokens": ["[PAD]", "[UNK]"]}
+{"model": "wordlevel", "vocab_size": 8287, "unk_token": "[UNK]", "special_tokens": ["[PAD]", "[UNK]"]}