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

  • Log In
  • Sign Up

DoDucAnh
/
MNLP_M2_document_encoder

Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:594028
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use DoDucAnh/MNLP_M2_document_encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use DoDucAnh/MNLP_M2_document_encoder with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("DoDucAnh/MNLP_M2_document_encoder")
    
    sentences = [
        "'আমি' শব্দটি কোন লিঙ্গ?\nA. উভয় লিঙ্গ\nB. ক্লীব লিঙ্গ\nC. পুংলিঙ্গ\nD. স্ত্রী লিঙ্গ",
        "F.P. Dobroslavin, tibbin müxtəlif sahələri üzrə tanınmış bir alimdir, ancaq daha çox baş vermiş tədqiqatlara görə seçilir. Onun əməyinin sanitar-gigiyenik sahəyə təsiri əhəmiyyətlidir.",
        "বাংলা ভাষায় শব্দগুলোর লিঙ্গ সাধারণত তিনটি মূল শ্রেণিতে ভাগ হয়: পুংলিঙ্গ (পুরুষ), স্ত্রী লিঙ্গ (মহিলা), এবং ক্লীব লিঙ্গ (যার কোনো লিঙ্গ নেই)।",
        "Waves are disturbances that transfer energy from one place to another without transferring matter. Think of a ripple on a pond – the water molecules don't travel across the pond with the ripple; they mostly move up and down as the energy passes through them."
    ]
    embeddings = model.encode(sentences)
    
    similarities = model.similarity(embeddings, embeddings)
    print(similarities.shape)
    # [4, 4]
  • Notebooks
  • Google Colab
  • Kaggle
MNLP_M2_document_encoder / checkpoint-49503
2.26 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
DoDucAnh's picture
DoDucAnh
Upload folder using huggingface_hub
8da4c75 verified over 1 year ago
  • 1_Pooling
    Upload folder using huggingface_hub over 1 year ago
  • README.md
    32.2 kB
    Upload folder using huggingface_hub over 1 year ago
  • config.json
    663 Bytes
    Upload folder using huggingface_hub over 1 year ago
  • config_sentence_transformers.json
    205 Bytes
    Upload folder using huggingface_hub over 1 year ago
  • model.safetensors
    2.24 GB
    xet
    Upload folder using huggingface_hub over 1 year ago
  • modules.json
    349 Bytes
    Upload folder using huggingface_hub over 1 year ago
  • rng_state.pth
    14.6 kB
    xet
    Upload folder using huggingface_hub over 1 year ago
  • sentence_bert_config.json
    53 Bytes
    Upload folder using huggingface_hub over 1 year ago
  • special_tokens_map.json
    964 Bytes
    Upload folder using huggingface_hub over 1 year ago
  • tokenizer.json
    17.1 MB
    xet
    Upload folder using huggingface_hub over 1 year ago
  • tokenizer_config.json
    1.21 kB
    Upload folder using huggingface_hub over 1 year ago
  • trainer_state.json
    8.31 kB
    Upload folder using huggingface_hub over 1 year ago
  • training_args.bin
    5.91 kB
    xet
    Upload folder using huggingface_hub over 1 year ago