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

NeuML
/
atto-28m-8192d-sparse-embeddings

Sentence Similarity
sentence-transformers
Safetensors
Transformers
English
atto
feature-extraction
sparse-encoder
custom_code
Model card Files Files and versions
xet
Community

Instructions to use NeuML/atto-28m-8192d-sparse-embeddings with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use NeuML/atto-28m-8192d-sparse-embeddings with sentence-transformers:

    from sentence_transformers import SparseEncoder
    
    model = SparseEncoder("NeuML/atto-28m-8192d-sparse-embeddings", trust_remote_code=True)
    
    queries = ["Which planet is known as the Red Planet?"]
    documents = [
    	"Venus is often called Earth's twin because of its similar size and proximity.",
    	"Mars, known for its reddish appearance, is often referred to as the Red Planet.",
    	"Jupiter, the largest planet in our solar system, has a prominent red spot.",
    ]
    
    query_embeddings = model.encode_query(queries)
    document_embeddings = model.encode_document(documents)
    
    similarities = model.similarity(query_embeddings, document_embeddings)
    print(similarities)
  • Transformers

    How to use NeuML/atto-28m-8192d-sparse-embeddings with Transformers:

    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("NeuML/atto-28m-8192d-sparse-embeddings", trust_remote_code=True, device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
atto-28m-8192d-sparse-embeddings
115 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
davidmezzetti's picture
davidmezzetti
Initial model
61054bb about 7 hours ago
  • 1_SpladePooling
    Initial model about 7 hours ago
  • .gitattributes
    1.52 kB
    initial commit about 7 hours ago
  • README.md
    3.09 kB
    Initial model about 7 hours ago
  • config.json
    612 Bytes
    Initial model about 7 hours ago
  • config_sentence_transformers.json
    292 Bytes
    Initial model about 7 hours ago
  • configuration_atto.py
    1.11 kB
    Initial model about 7 hours ago
  • model.safetensors
    114 MB
    xet
    Initial model about 7 hours ago
  • modeling_atto.py
    11.4 kB
    Initial model about 7 hours ago
  • modules.json
    290 Bytes
    Initial model about 7 hours ago
  • sentence_bert_config.json
    241 Bytes
    Initial model about 7 hours ago
  • tokenizer.json
    701 kB
    Initial model about 7 hours ago
  • tokenizer_config.json
    350 Bytes
    Initial model about 7 hours ago