add sts sentence transformers (ko, ja, zh)

sts/ja/jasbert.base/1_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
+}

sts/ja/jasbert.base/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/root/.pororo/sbert/jasbert.base.ja.nli.sts/0_Transformer",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

sts/ja/jasbert.base/config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.0",
+    "transformers": "4.17.0",
+    "pytorch": "1.6.0"
+  }
+}

sts/ja/jasbert.base/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sts/ja/jasbert.base/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd08bb94edf13311f390ce0aa7d559576d40677bd23135afe53510dcb9d7fd9
+size 442553975

sts/ja/jasbert.base/sentence_bert_config.json

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

sts/ja/jasbert.base/special_tokens_map.json

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

sts/ja/jasbert.base/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "wordpiece", "mecab_kwargs": {"mecab_option": "-r \"/opt/conda/lib/python3.7/site-packages/ipadic/dicdir/mecabrc\" -d \"/opt/conda/lib/python3.7/site-packages/ipadic/dicdir\""}, "model_max_length": 512, "special_tokens_map_file": "new_output/training_nli_cl-tohoku-bert-base-japanese-whole-word-masking/0_Transformer/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "/root/.pororo/sbert/jasbert.base.ja.nli.sts/0_Transformer", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

sts/ko/brainsbert.base/0_BrainRoBERTa/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/root/.pororo/sbert/brainsbert.base.ko.kornli.korsts/0_BrainRoBERTa",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32002
+}

sts/ko/brainsbert.base/0_BrainRoBERTa/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a13407ff4b00a8d729ecf8887ad57add468ee795f55b9f7fd26147c56feacc4
+size 442563191

sts/ko/brainsbert.base/0_BrainRoBERTa/sentence_brain_roberta_config.json

@@ -0,0 +1,3 @@
+{
+  "max_seq_length": 128
+}

sts/ko/brainsbert.base/1_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
+}

sts/ko/brainsbert.base/config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.0",
+    "transformers": "4.17.0",
+    "pytorch": "1.6.0"
+  }
+}

sts/ko/brainsbert.base/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "0_BrainRoBERTa",
+    "type": "pororo.models.brainsbert.BrainRoBERTa"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sts/zh/zhsbert.base/1_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
+}

sts/zh/zhsbert.base/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/root/.pororo/sbert/zhsbert.base.zh.nli.sts/0_Transformer",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

sts/zh/zhsbert.base/config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.0",
+    "transformers": "4.17.0",
+    "pytorch": "1.6.0"
+  }
+}

sts/zh/zhsbert.base/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sts/zh/zhsbert.base/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bfe1955f00f94ce29bc92a0ada34ce74ae9b4c440d3c75cb50b84da62212f9
+size 409155191

sts/zh/zhsbert.base/sentence_bert_config.json

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

sts/zh/zhsbert.base/special_tokens_map.json

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

sts/zh/zhsbert.base/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "output/training_nli_bert-base-chinese/0_Transformer/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "/root/.pororo/sbert/zhsbert.base.zh.nli.sts/0_Transformer", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}