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

Omartificial-Intelligence-Space
/
Arabic-Triplet-Matryoshka-V2

Feature Extraction
sentence-transformers
Safetensors
Transformers.js
Transformers
Arabic
bert
sentence-similarity
dataset_size:75000
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
mteb
text-embeddings-inference
Model card Files Files and versions
xet
Community
2

Instructions to use Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2 with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2")
    
    sentences = [
        "The weather is lovely today.",
        "It's so sunny outside!",
        "He drove to the stadium."
    ]
    embeddings = model.encode(sentences)
    
    similarities = model.similarity(embeddings, embeddings)
    print(similarities.shape)
    # [3, 3]
  • Transformers.js

    How to use Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2 with Transformers.js:

    // npm i @huggingface/transformers
    import { pipeline } from '@huggingface/transformers';
    
    // Allocate pipeline
    const pipe = await pipeline('feature-extraction', 'Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2');
  • Transformers

    How to use Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2 with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("feature-extraction", model="Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2")
    # Load model directly
    from transformers import AutoTokenizer, AutoModel
    
    tokenizer = AutoTokenizer.from_pretrained("Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2")
    model = AutoModel.from_pretrained("Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2")
  • Inference
  • Notebooks
  • Google Colab
  • Kaggle
Arabic-Triplet-Matryoshka-V2
543 MB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 22 commits
Omartificial-Intelligence-Space's picture
Omartificial-Intelligence-Space
Update README.md
408d483 verified 9 months ago
  • 1_Pooling
    Add new SentenceTransformer model. almost 2 years ago
  • .gitattributes
    1.52 kB
    initial commit almost 2 years ago
  • README.md
    6.98 kB
    Update README.md 9 months ago
  • config.json
    637 Bytes
    Add new SentenceTransformer model. almost 2 years ago
  • config_sentence_transformers.json
    195 Bytes
    Add new SentenceTransformer model. almost 2 years ago
  • model.safetensors
    541 MB
    xet
    Add new SentenceTransformer model. almost 2 years ago
  • modules.json
    229 Bytes
    Add new SentenceTransformer model. almost 2 years ago
  • sentence_bert_config.json
    53 Bytes
    Add new SentenceTransformer model. almost 2 years ago
  • special_tokens_map.json
    695 Bytes
    Add new SentenceTransformer model. almost 2 years ago
  • tokenizer.json
    1.78 MB
    Add new SentenceTransformer model. almost 2 years ago
  • tokenizer_config.json
    1.83 kB
    Add new SentenceTransformer model. almost 2 years ago
  • vocab.txt
    761 kB
    Add new SentenceTransformer model. almost 2 years ago