Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

inkoziev
/
sbert_synonymy

Sentence Similarity
sentence-transformers
PyTorch
Transformers
Russian
bert
feature-extraction
text-embeddings-inference
Model card Files Files and versions
xet
Community
2

Instructions to use inkoziev/sbert_synonymy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use inkoziev/sbert_synonymy with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("inkoziev/sbert_synonymy")
    
    sentences = [
        "Кошка ловит мышку",
        "Мышка преследуема кошкой",
        "Кошка гонится за мышью",
        "Кошка ловит кайф"
    ]
    embeddings = model.encode(sentences)
    
    similarities = model.similarity(embeddings, embeddings)
    print(similarities.shape)
    # [4, 4]
  • Transformers

    How to use inkoziev/sbert_synonymy with Transformers:

    # Load model directly
    from transformers import AutoTokenizer, AutoModel
    
    tokenizer = AutoTokenizer.from_pretrained("inkoziev/sbert_synonymy")
    model = AutoModel.from_pretrained("inkoziev/sbert_synonymy")
  • Notebooks
  • Google Colab
  • Kaggle
sbert_synonymy
Ctrl+K
Ctrl+K
  • 3 contributors
History: 10 commits
koziev ilya
new samples in training dataset
fa4f459 about 3 years ago
  • 1_Pooling
    first release of the tiny model for paraphrase detection over 3 years ago
  • .gitattributes
    1.43 kB
    initial commit over 3 years ago
  • README.md
    3.71 kB
    Add metadata for dataset used to train model (#1) over 3 years ago
  • config.json
    684 Bytes
    model retrained after dataset expansion over 3 years ago
  • config_sentence_transformers.json
    135 Bytes
    model retrained after dataset expansion over 3 years ago
  • modules.json
    229 Bytes
    first release of the tiny model for paraphrase detection over 3 years ago
  • pytorch_model.bin

    Detected Pickle imports (4)

    • "collections.OrderedDict",
    • "torch._utils._rebuild_tensor_v2",
    • "torch.LongStorage",
    • "torch.FloatStorage"

    What is a pickle import?

    117 MB
    xet
    new samples in training dataset about 3 years ago
  • sentence_bert_config.json
    54 Bytes
    first release of the tiny model for paraphrase detection over 3 years ago
  • special_tokens_map.json
    125 Bytes
    first release of the tiny model for paraphrase detection over 3 years ago
  • tokenizer.json
    2.41 MB
    first release of the tiny model for paraphrase detection over 3 years ago
  • tokenizer_config.json
    410 Bytes
    first release of the tiny model for paraphrase detection over 3 years ago
  • vocab.txt
    1.08 MB
    first release of the tiny model for paraphrase detection over 3 years ago