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

HelloSun
/
fint-epqv2

llama.cpp
flint
Mixture of Experts
expert-offloading
cpu-inference
Model card Files Files and versions
xet
Community
fint-epqv2
2.52 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 18 commits
HelloSun's picture
HelloSun
Add auto arena mode (80% of available memory, capped at all experts); patch 369ef971
2873e19 verified 14 days ago
  • docs
    Add auto arena mode (80% of available memory, capped at all experts); patch 369ef971 14 days ago
  • results
    Add auto arena mode (80% of available memory, capped at all experts); patch 369ef971 14 days ago
  • src
    Add auto arena mode (80% of available memory, capped at all experts); patch 369ef971 14 days ago
  • tools
    Fix runmem threshold unit bug; re-run all memory tiers enforced (native, v1, v2, v2 forced); add native data and forced-vs-designed explanation 14 days ago
  • .gitattributes
    1.52 kB
    initial commit 14 days ago
  • README.md
    3.84 kB
    Add auto arena mode (80% of available memory, capped at all experts); patch 369ef971 14 days ago
  • bench.sh
    1.23 kB
    Upload v2 memory tiers (default and forced row-parallel) with path counters 14 days ago
  • flint-epq.patch
    212 kB
    Add auto arena mode (80% of available memory, capped at all experts); patch 369ef971 14 days ago