pytorch model

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
+}

README.txt

@@ -0,0 +1,25 @@
+# cased Finnish Sentence BERT model
+
+Finnish Sentence BERT trained from FinBERT
+
+## Training
+
+    FinBERT model: TurkuNLP/bert-base-finnish-cased-v1
+    Data: The data provided [here] (https://turkunlp.org/paraphrase.html), including the Finnish Paraphrase Corpus and the automatically collected paraphrase candidates (500K positive and 5M negative)
+    Pooling: mean pooling
+    Task: Binary prediction, whether two sentences are paraphrases or not. Note: the labels 3 and 4 are considered paraphrases, and labels 1 and 2 non-paraphrases. [Details on labels] (https://aclanthology.org/2021.nodalida-main.29/)
+
+## Usage
+
+Please refer to the [HuggingFace documentation] (https://huggingface.co/sentence-transformers/bert-base-nli-mean-tokens)
+
+Briefly, using the `SentenceTransformer` library,
+
+```
+from sentence_transformers import SentenceTransformer
+sentences = ["Tämä on esimerkkilause.", "Tämä on toinen lause."]
+
+model = SentenceTransformer('sbert-cased-finnish-paraphrase')
+embeddings = model.encode(sentences)
+print(embeddings)
+```

config.json

@@ -0,0 +1,3 @@
+{
+  "__version__": "0.2.3"
+}

modules.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1599b1aa408f2ffd35cce5c2e1310c5190b942af976a955765a56ff051f1f50
+size 498140020

sentence_bert_config.json

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

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": false, "do_basic_tokenize": true, "never_split": null, "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": null, "tokenizer_file": "/users/changlih/.cache/huggingface/transformers/3583dbf83678cb60c5faaf0a07aa0d452fc4ec09aac87b8680027bf79b1a6270.e49785bf2de92e06a4d89026870d6979723c8e64cfc9311596ca5b9a3b56289e", "name_or_path": "TurkuNLP/bert-base-finnish-cased-v1"}