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

ZichenAI
/
layazh-zh

Text Classification
Transformers
Safetensors
Chinese
laya
system-one
calibrated-decisions
rlcd
chinese
classification
routing
scoring
guardrails
non-autoregressive
commercial-license-required
Model card Files Files and versions
xet
Community

Instructions to use ZichenAI/layazh-zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use ZichenAI/layazh-zh with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="ZichenAI/layazh-zh")
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("ZichenAI/layazh-zh", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
layazh-zh
1.41 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
NovaAI
docs: specific RLCD recipe (reward weights, group/sigma/tau, lr, unfrozen layers); temperature-clamp note
769ee58 verified 2 days ago
  • encoder
    layazh-zh: Chinese System-1 decision model (Laya recipe, RoBERTa-large encoder + decision head); full-eval acc 0.6951 vs upstream 0.4783 2 days ago
  • tokenizer
    layazh-zh: Chinese System-1 decision model (Laya recipe, RoBERTa-large encoder + decision head); full-eval acc 0.6951 vs upstream 0.4783 2 days ago
  • .gitattributes
    1.52 kB
    initial commit 2 days ago
  • LICENSE
    4.1 kB
    docs: friendlier usage example, installation section, license threshold 1万 2 days ago
  • README.md
    20.9 kB
    docs: specific RLCD recipe (reward weights, group/sigma/tau, lr, unfrozen layers); temperature-clamp note 2 days ago
  • layazh-0.1.0-py3-none-any.whl
    25.9 kB
    add installable wheel (layazh 0.1.0); docs: installation + installable package 2 days ago
  • layazh-0.1.0.tar.gz
    31.8 kB
    xet
    add installable wheel (layazh 0.1.0); docs: installation + installable package 2 days ago
  • model.safetensors
    1.41 GB
    xet
    layazh-zh: Chinese System-1 decision model (Laya recipe, RoBERTa-large encoder + decision head); full-eval acc 0.6951 vs upstream 0.4783 2 days ago
  • rl_agent_config.json
    2.06 kB
    layazh-zh: Chinese System-1 decision model (Laya recipe, RoBERTa-large encoder + decision head); full-eval acc 0.6951 vs upstream 0.4783 2 days ago