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
creativityschapiro 's Collections
CreativityNeuro: Optimal Configs
Phi-3-Medium-Instruct-Creative
Llama-3.2-3B-Instruct-Creative
Qwen-2.5-7B-Instruct-Creative
Phi-3-Small-8k-Instruct-Creative
Qwen-2.5-14B-Instruct-Creative
Qwen-2.5-3B-Instruct-Creative
Llama-3.1-8B-Instruct-Creative
Phi-3.5-Mini-Instruct-Creative
Llama-3.2-1B-Instruct-Creative

CreativityNeuro: Optimal Configs

updated about 3 hours ago

Best CreativityNeuro configuration per model across creativity tasks. ρ = keep_ratio (mask sparsity), α = amplification strength.

Upvote
-

  • creativityschapiro/phi-3.5-mini-instruct-cn-dat-kr0.1-a1.0-creative

    4B • Updated Feb 2 • 4

    Note ρ = 0.10, α = 1.0


  • creativityschapiro/qwen2.5-7b-instruct-cn-dat-kr0.1-a1.0-creative

    8B • Updated Feb 11 • 7

    Note ρ = 0.10, α = 1.0


  • creativityschapiro/qwen2.5-14b-instruct-cn-dat-kr0.05-a1.0-creative

    15B • Updated Feb 10 • 8

    Note ρ = 0.05, α = 1.0


  • creativityschapiro/llama-3.1-8b-instruct-cn-dat-kr0.1-a1.0-creative

    8B • Updated Feb 3 • 4

    Note ρ = 0.10, α = 1.0


  • creativityschapiro/phi-3-medium-4k-instruct-cn-dat-kr0.01-a2.0-creative

    14B • Updated Feb 12 • 5

    Note ρ = 0.01, α = 2.0


  • creativityschapiro/llama-3.2-3b-instruct-cn-dat-kr0.05-a1.0-creative

    3B • Updated Feb 11 • 4

    Note ρ = 0.05, α = 1.0

Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs