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

toonist
/
AnuLM-Base-400M

Text Generation
Safetensors
PyTorch
Hindi
English
anulm
mixture-of-experts
Mixture of Experts
hindi
indic
small-language-model
sarvam-architecture
custom_code
Model card Files Files and versions
xet
Community
1
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

The 38.7% active vocabulary tax, micro-expert margin collapse, and sliding-window limits in 400M Sarvam scaling

#1 opened about 12 hours ago by
AndrewThompson1233
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs