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
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

larsksy
/
norbert4-large-scandinavian-embedding

Sentence Similarity
sentence-transformers
Safetensors
Norwegian
Danish
Swedish
feature-extraction
dense
Generated from Trainer
dataset_size:1032261
loss:MultipleNegativesRankingLoss
custom_code
Model card Files Files and versions
xet
Community

Instructions to use larsksy/norbert4-large-scandinavian-embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use larsksy/norbert4-large-scandinavian-embedding with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("larsksy/norbert4-large-scandinavian-embedding", trust_remote_code=True)
    
    sentences = [
        "\n    \nHva med litt moo goo gai pan?\n    \n  ",
        "\n    \nHvad med noget moo goo gai pan?\n    \n  ",
        "Vi må dog med en vis beklagelse bemærke, at institutionsreformerne, den kommende finansiering af budgettet og andre problemer stadig spøger i kulissen, hvorimod en entydig politisk vilje ville have ført til et krav om, at regeringerne behandler europæiske anliggender på en politisk måde og ikke som en rent økonomisk og finansiel forhandling.\n",
        "\n- Hvem fanden var det, du kyssede?\n    \n  "
    ]
    embeddings = model.encode(sentences)
    
    similarities = model.similarity(embeddings, embeddings)
    print(similarities.shape)
    # [4, 4]
  • Notebooks
  • Google Colab
  • Kaggle
norbert4-large-scandinavian-embedding
1.44 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
larsksy's picture
larsksy
Upload folder using huggingface_hub
4d87ffe verified 8 months ago
  • 1_Pooling
    Upload folder using huggingface_hub 8 months ago
  • .gitattributes
    1.52 kB
    initial commit 8 months ago
  • README.md
    45.8 kB
    Upload folder using huggingface_hub 8 months ago
  • config.json
    1.39 kB
    Upload folder using huggingface_hub 8 months ago
  • config_sentence_transformers.json
    283 Bytes
    Upload folder using huggingface_hub 8 months ago
  • configuration_gptbert.py
    1.01 kB
    Upload folder using huggingface_hub 8 months ago
  • model.safetensors
    1.44 GB
    xet
    Upload folder using huggingface_hub 8 months ago
  • modeling_gptbert.py
    47.6 kB
    Upload folder using huggingface_hub 8 months ago
  • modules.json
    229 Bytes
    Upload folder using huggingface_hub 8 months ago
  • sentence_bert_config.json
    57 Bytes
    Upload folder using huggingface_hub 8 months ago
  • special_tokens_map.json
    965 Bytes
    Upload folder using huggingface_hub 8 months ago
  • tokenizer.json
    3.63 MB
    Upload folder using huggingface_hub 8 months ago
  • tokenizer_config.json
    3.12 kB
    Upload folder using huggingface_hub 8 months ago