Add Japanese Sentence-BERT model

added_tokens.json

@@ -0,0 +1 @@
+{}

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_labels": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_past": true,
+  "pruned_heads": {},
+  "torchscript": false,
+  "type_vocab_size": 2,
+  "use_bfloat16": false,
+  "vocab_size": 32000
+}

pooling_config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a1866b5e7cb9fe116750da0dbb6442f1caf5dd399fee2411ede8c5f6a05936
+size 442517175

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": true
+}

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 @@
+{"do_lower_case": true, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "wordpiece", "max_len": 512, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "init_inputs": []}