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

Spaces:
DerAuctor
/
kev-9b
Paused

App Files Files Community
Fetching metadata from the HF Docker repository...
kev-9b
75.5 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
DerAuctor's picture
DerAuctor
Validate before the GPU call, so an invalid request costs no GPU time
7c16176 verified about 1 month ago
  • kev
    Kev-9B demo + systemone API (vendored kev code from jaredpalmer/kev) about 1 month ago
  • .gitattributes
    1.52 kB
    initial commit about 1 month ago
  • README.md
    3.51 kB
    Mark context-overflow errors as invalid requests, like validation errors about 1 month ago
  • app.py
    19.7 kB
    Validate before the GPU call, so an invalid request costs no GPU time about 1 month ago
  • presets.py
    6.39 kB
    Kev-9B demo + systemone API (vendored kev code from jaredpalmer/kev) about 1 month ago
  • requirements.txt
    76 Bytes
    Drop flash-linear-attention (25 s Triton compile per cold worker for 5 ms warm gain); GPU duration 20 s from measurement about 1 month ago