Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "do_nfkc": false,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "megagonlabs/transformers-ud-japanese-electra-base-discriminator",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--megagonlabs--transformers-ud-japanese-electra-base-discriminator/snapshots/96a3711b754c2caf0d1e22b30cbb893a37fa46c2/special_tokens_map.json",
+  "subword_tokenizer_type": "wordpiece",
+  "sudachipy_kwargs": {
+    "dict_type": "core",
+    "split_mode": "A"
+  },
+  "tokenizer_class": "ElectraSudachipyTokenizer",
+  "unk_token": "[UNK]",
+  "word_form_type": "dictionary_and_surface",
+  "word_tokenizer_type": "sudachipy"
+}