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

sewoong
/
korean-neural-sparse-encoder

Fill-Mask
Transformers
Safetensors
Korean
modernbert
neural-sparse
splade
opensearch
korean
information-retrieval
e-commerce
Model card Files Files and versions
xet
Community

Instructions to use sewoong/korean-neural-sparse-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use sewoong/korean-neural-sparse-encoder with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("fill-mask", model="sewoong/korean-neural-sparse-encoder")
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForMaskedLM
    
    tokenizer = AutoTokenizer.from_pretrained("sewoong/korean-neural-sparse-encoder")
    model = AutoModelForMaskedLM.from_pretrained("sewoong/korean-neural-sparse-encoder")
  • Notebooks
  • Google Colab
  • Kaggle
korean-neural-sparse-encoder
604 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 24 commits
sewoong's picture
sewoong
docs: use English only in README (remove Korean descriptions)
abda9be verified 2 months ago
  • finetune
    Add fine-tuning toolkit: CONTRIBUTING.md 2 months ago
  • .gitattributes
    1.57 kB
    Update to V26: Recall@1 40.7% (+44% vs V25) 4 months ago
  • README.md
    7.32 kB
    docs: use English only in README (remove Korean descriptions) 2 months ago
  • added_tokens.json
    21 Bytes
    v22.0: InfoNCE contrastive loss, temperature annealing, 99.87% recall 4 months ago
  • config.json
    1.2 kB
    Korean neural sparse encoder: SPLADE-max with ModernBERT backbone 3 months ago
  • model.safetensors
    598 MB
    xet
    feat: update to V33-ecom-v6 (e-commerce fine-tuned) 2 months ago
  • sentencepiece.bpe.model
    5.07 MB
    xet
    Update to V26: Recall@1 40.7% (+44% vs V25) 4 months ago
  • special_tokens_map.json
    969 Bytes
    Korean neural sparse encoder: SPLADE-max with ModernBERT backbone 3 months ago
  • tokenizer.json
    1.09 MB
    xet
    Korean neural sparse encoder: SPLADE-max with ModernBERT backbone 3 months ago
  • tokenizer_config.json
    6.95 kB
    Korean neural sparse encoder: SPLADE-max with ModernBERT backbone 3 months ago
  • vocab.txt
    290 kB
    v22.0: InfoNCE contrastive loss, temperature annealing, 99.87% recall 4 months ago