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

dfrokido
/
bge-large-e8-snap

Feature Extraction
sentence-transformers
Safetensors
English
bert
sentence-similarity
e8-lattice
rf-snap
latticememory
Eval Results (legacy)
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use dfrokido/bge-large-e8-snap with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use dfrokido/bge-large-e8-snap with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("dfrokido/bge-large-e8-snap")
    
    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]
  • Notebooks
  • Google Colab
  • Kaggle
bge-large-e8-snap
1.34 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 18 commits
dfrokido's picture
dfrokido
Clarify E8 key is an added lookup layer, not a footprint reduction: the full embedding is retained in every mode and never discarded
fc0c33a verified 3 days ago
  • 1_Pooling
    Add new SentenceTransformer model about 1 month ago
  • .gitattributes
    1.52 kB
    initial commit about 1 month ago
  • README.md
    5.38 kB
    Clarify E8 key is an added lookup layer, not a footprint reduction: the full embedding is retained in every mode and never discarded 3 days ago
  • config.json
    860 Bytes
    Add new SentenceTransformer model about 1 month ago
  • config_sentence_transformers.json
    295 Bytes
    Add new SentenceTransformer model about 1 month ago
  • model.safetensors
    1.34 GB
    xet
    Add new SentenceTransformer model about 1 month ago
  • modeling_e8_snap.py
    6.55 kB
    fix: rebrand to RF-Snap (Resonance Folding), fix docstring, clean up about 1 month ago
  • modules.json
    290 Bytes
    Add new SentenceTransformer model about 1 month ago
  • rf_snap_demo.ipynb
    10.9 kB
    demo: add RF-Snap Colab notebook (CPU, no GPU required) about 1 month ago
  • sentence_bert_config.json
    250 Bytes
    Add new SentenceTransformer model about 1 month ago
  • tokenizer.json
    712 kB
    Add new SentenceTransformer model about 1 month ago
  • tokenizer_config.json
    658 Bytes
    Add new SentenceTransformer model about 1 month ago