Upload tokenizer

special_tokens_map.json

@@ -1,8 +1,11 @@
 {
-  "additional_special_tokens": [
-    "[URL]",
-    "[USER]"
-  ],
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
     "content": "[CLS]",
     "lstrip": false,
@@ -10,6 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "[MASK]",
     "lstrip": false,

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4f774d877b61859dd2df012b51de4f25a0ee46b30b5dbaa886530efec6fc68
+size 969814

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553c7d94babbd19461d019eef9ff56f66d41058ffdad0e3a81d09b6781d30889
-size 17098348
+oid sha256:92b9a8ca700480bf52a97c4dbf7ba5752cda0b008af756f8f20a7fc64acb574b
+size 3381622

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[UNK]",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "[SEP]",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "[PAD]",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": true
     },
     "3": {
-      "content": "[CLS]",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -39,54 +39,20 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "5": {
-      "content": "[URL]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "[USER]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "31999": {
-      "content": "\n",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
-  "additional_special_tokens": [
-    "[URL]",
-    "[USER]"
-  ],
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,
-  "do_subword_tokenize": true,
-  "do_word_tokenize": true,
-  "jumanpp_kwargs": null,
-  "keep_newlines": true,
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "mecab_kwargs": {
-    "mecab_dic": "unidic_lite"
-  },
-  "model_max_length": 512,
-  "never_split": null,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "subword_tokenizer_type": "wordpiece",
-  "sudachi_kwargs": null,
-  "tokenizer_class": "BertJapaneseTokenizer",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
   "unk_token": "[UNK]",
-  "word_tokenizer_type": "mecab"
+  "vocab_type": "spm"
 }