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 +1,60 @@
+# Uncased Finnish Sentence BERT model
+
+Finnish Sentence BERT trained from FinBERT
+
+## Training
+
+    FinBERT model: TurkuNLP/bert-base-finnish-uncased-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
+
+The same as in [HuggingFace documentation] (https://huggingface.co/sentence-transformers/bert-base-nli-mean-tokens). Either through `SentenceTransformer` or `HuggingFace Transformers`
+
+### SentenceTransformer
+
+```
+from sentence_transformers import SentenceTransformer
+sentences = ["Tämä on esimerkkilause.", "Tämä on toinen lause."]
+
+model = SentenceTransformer('TurkuNLP/sbert-uncased-finnish-paraphrase')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+### HuggingFace Transformers
+
+```
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ["Tämä on esimerkkilause.", "Tämä on toinen lause."]
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('TurkuNLP/sbert-uncased-finnish-paraphrase')
+model = AutoModel.from_pretrained('TurkuNLP/sbert-uncased-finnish-paraphrase')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```

added_tokens.json

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

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "TurkuNLP/bert-base-finnish-uncased-v1",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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",
+  "transformers_version": "4.4.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50101
+}

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:cb4b16cbfeed535c1ec01bc33d11d178bef1373e51e20d893c1add27abeac658
+size 498127732

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, "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, "name_or_path": "TurkuNLP/bert-base-finnish-uncased-v1"}