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

Dunde
/
laya-tf-judge

Text Classification
ONNX
Laya
Korean
system-one
calibrated-decisions
onnxruntime-web
korean
vocabulary-pruning
Model card Files Files and versions
xet
Community

Instructions to use Dunde/laya-tf-judge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Laya

    How to use Dunde/laya-tf-judge with Laya:

    # No code snippets available yet for this library.
    
    # To use this model, check the repository files and the library's documentation.
    
    # Want to help? PRs adding snippets are welcome at:
    # https://github.com/huggingface/huggingface.js
  • Notebooks
  • Google Colab
  • Kaggle
laya-tf-judge
186 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
Dunde's picture
Dunde
Retrain on 5-50 character replies with a wider T definition (distancing replies count as T); soft-ce, temperature 2.879
2806fd1 verified 21 days ago
  • onnx
    Retrain on 5-50 character replies with a wider T definition (distancing replies count as T); soft-ce, temperature 2.879 21 days ago
  • .gitattributes
    1.57 kB
    Laya Multilingual fine-tuned for T/F reply focus, 8-bit ONNX for the browser 21 days ago
  • LICENSE
    10.2 kB
    Laya Multilingual fine-tuned for T/F reply focus, 8-bit ONNX for the browser 21 days ago
  • README.md
    11.3 kB
    Retrain on 5-50 character replies with a wider T definition (distancing replies count as T); soft-ce, temperature 2.879 21 days ago
  • questions.json
    431 Bytes
    Laya Multilingual fine-tuned for T/F reply focus, 8-bit ONNX for the browser 21 days ago
  • rl_agent_config.json
    1.95 kB
    Retrain on 5-50 character replies with a wider T definition (distancing replies count as T); soft-ce, temperature 2.879 21 days ago
  • tokenizer.json
    1.67 MB
    xet
    Prune vocabulary to 39,001 Korean-focused tokens (download ~370 MB -> ~189 MB, same outputs on 298 eval items) 21 days ago
  • tokenizer_config.json
    595 Bytes
    Laya Multilingual fine-tuned for T/F reply focus, 8-bit ONNX for the browser 21 days ago