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

DiTy
/
bi-encoder-russian-msmarco

Sentence Similarity
sentence-transformers
Safetensors
Transformers
Russian
bert
feature-extraction
rubert
bi-encoder
retriever
msmarco
Eval Results (legacy)
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use DiTy/bi-encoder-russian-msmarco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use DiTy/bi-encoder-russian-msmarco with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("DiTy/bi-encoder-russian-msmarco")
    
    sentences = [
        "определение новичка",
        "Часть пятая: Посещение художественного музея. Для новичка посещение художественного музея может стать непростой задачей. Большинство музеев очень большие и требуют выносливости и хорошего чувства направления. Потратьте некоторое время на то, чтобы узнать больше о музее, прежде чем отправиться в путь, - лучший способ обеспечить более информативное и приятное посещение. ПРЕЖДЕ ЧЕМ ТЫ УЙДЕШЬ.",
        "Определение новичка - это новичок или человек в начале чего-либо."
    ]
    embeddings = model.encode(sentences)
    
    similarities = model.similarity(embeddings, embeddings)
    print(similarities.shape)
    # [3, 3]
  • Transformers

    How to use DiTy/bi-encoder-russian-msmarco with Transformers:

    # Load model directly
    from transformers import AutoTokenizer, AutoModel
    
    tokenizer = AutoTokenizer.from_pretrained("DiTy/bi-encoder-russian-msmarco")
    model = AutoModel.from_pretrained("DiTy/bi-encoder-russian-msmarco")
  • Inference
  • Notebooks
  • Google Colab
  • Kaggle
bi-encoder-russian-msmarco
Ctrl+K
Ctrl+K
  • 1 contributor
History: 12 commits
DiTy's picture
DiTy
Update README.md
34530ed verified almost 2 years ago
  • 1_Pooling
    Init bi-encoder about 2 years ago
  • .gitattributes
    1.52 kB
    initial commit about 2 years ago
  • README.md
    10.2 kB
    Update README.md almost 2 years ago
  • config.json
    920 Bytes
    Init bi-encoder about 2 years ago
  • config_sentence_transformers.json
    165 Bytes
    Init bi-encoder about 2 years ago
  • model.safetensors
    711 MB
    xet
    Init bi-encoder about 2 years ago
  • modules.json
    229 Bytes
    Init bi-encoder about 2 years ago
  • sentence_bert_config.json
    53 Bytes
    Init bi-encoder about 2 years ago
  • special_tokens_map.json
    695 Bytes
    Init bi-encoder about 2 years ago
  • tokenizer.json
    3.57 MB
    Init bi-encoder about 2 years ago
  • tokenizer_config.json
    1.27 kB
    Init bi-encoder about 2 years ago
  • vocab.txt
    1.65 MB
    Init bi-encoder about 2 years ago