pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer
sentences = ["Det här är en exempelmening", "Varje exempel blir konverterad"]

model = SentenceTransformer('KBLab/sentence-bert-swedish-cased')
embeddings = model.encode(sentences)
print(embeddings)

git clone --depth 1 --branch v1.0 https://huggingface.co/KBLab/sentence-bert-swedish-cased

from sentence_transformers import SentenceTransformer
model = SentenceTransformer("path_to_model_folder/sentence-bert-swedish-cased")

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 = ['Det här är en exempelmening', 'Varje exempel blir konverterad']

# Load model from HuggingFace Hub
# To load an older version, e.g. v1.0, add the argument revision="v1.0" 
tokenizer = AutoTokenizer.from_pretrained('KBLab/sentence-bert-swedish-cased')
model = AutoModel.from_pretrained('KBLab/sentence-bert-swedish-cased')

# 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, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

AutoTokenizer.from_pretrained('KBLab/sentence-bert-swedish-cased', revision="v1.0")
AutoModel.from_pretrained('KBLab/sentence-bert-swedish-cased', revision="v1.0")

from sentence_transformers import SentenceTransformer
import pandas as pd

df = pd.read_csv(
    "sweparaphrase-dev-165.csv",
    sep="\t",
    header=None,
    names=[
        "original_id",
        "source",
        "type",
        "sentence_swe1",
        "sentence_swe2",
        "score",
        "sentence1",
        "sentence2",
    ],
)

model = SentenceTransformer("KBLab/sentence-bert-swedish-cased")

sentences1 = df["sentence_swe1"].tolist()
sentences2 = df["sentence_swe2"].tolist()

# Compute embedding for both lists
embeddings1 = model.encode(sentences1, convert_to_tensor=True)
embeddings2 = model.encode(sentences2, convert_to_tensor=True)

# Compute cosine similarity after normalizing
embeddings1 /= embeddings1.norm(dim=-1, keepdim=True)
embeddings2 /= embeddings2.norm(dim=-1, keepdim=True)

cosine_scores = embeddings1 @ embeddings2.t()
sentence_pair_scores = cosine_scores.diag()

df["model_score"] = sentence_pair_scores.cpu().tolist()
print(df[["score", "model_score"]].corr(method="spearman"))
print(df[["score", "model_score"]].corr(method="pearson"))

{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

{
    "epochs": 2,
    "evaluation_steps": 1000,
    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "",
    "optimizer_params": {
        "eps": 1e-06,
        "lr": 8e-06
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 5000,
    "weight_decay": 0.01
}

SentenceTransformer(
  (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'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})
)

@misc{rekathati2021introducing,  
  author = {Rekathati, Faton},  
  title = {The KBLab Blog: Introducing a Swedish Sentence Transformer},  
  url = {https://kb-labb.github.io/posts/2021-08-23-a-swedish-sentence-transformer/},  
  year = {2021}  
}