Upload 4 files

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "megagonlabs/transformers-ud-japanese-electra-base-ginza-520",
+  "architectures": [
+    "ElectraModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 0.0,
+  "max_position_embeddings": 512,
+  "model_name": "base",
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "vocab_size": 30112
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+    "do_lower_case": false,
+    "do_nfkc": false,
+    "do_word_tokenize": true,
+    "do_subword_tokenize": true,
+    "word_tokenizer_type": "sudachi",
+    "subword_tokenizer_type": "wordpiece",
+    "unk_token": "[UNK]",
+    "sep_token": "[SEP]",
+    "pad_token": "[PAD]",
+    "cls_token": "[CLS]",
+    "mask_token": "[MASK]",
+    "word_form_type": "dictionary_and_surface",
+    "sudachi_kwargs": {
+        "sudachi_split_mode": "A",
+        "sudachi_dict_type": "core"
+    },
+    "use_fast": false,
+    "tokenizer_class": "BertJapaneseTokenizer"
+}