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

infosave
/
humanizer-cmf

Text Generation
cortiq
English
Chinese
cmf
humanizer
text-rewriting
gemma4
quantized
Model card Files Files and versions
xet
Community

Instructions to use infosave/humanizer-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • cortiq

    How to use infosave/humanizer-cmf with cortiq:

    # one Rust binary, no additional dependencies
    cargo install cortiq-cli   # or a prebuilt binary from github.com/infosave2007/cmf/releases
    hf download infosave/humanizer-cmf --include "*.cmf" --local-dir .
    ls *.cmf                   # some repos ship more than one quantization
    cortiq run FILE.cmf --prompt "What is the capital of France?"
    cortiq serve FILE.cmf --port 8080   # OpenAI-compatible server
  • Notebooks
  • Google Colab
  • Kaggle
humanizer-cmf
19.9 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 6 commits
infosave's picture
infosave
Vulkan numbers with the batched Gemma-4 prompt graph (cortiq 0.8.16)
4ffba5d verified about 12 hours ago
  • .gitattributes
    1.64 kB
    humanizer 12B in CMF: q8_2f (default) and q4tp-ffn about 14 hours ago
  • README.md
    37.5 kB
    Vulkan numbers with the batched Gemma-4 prompt graph (cortiq 0.8.16) about 12 hours ago
  • humanizer-12b-q4tp-ffn.cmf
    7.89 GB
    xet
    Files carry max_tokens=2048 in their sampling defaults (cortiq 0.8.16 serve uses it); weights unchanged about 12 hours ago
  • humanizer-12b-q4tp-ffn.cmf.sha256
    93 Bytes
    Files carry max_tokens=2048 in their sampling defaults (cortiq 0.8.16 serve uses it); weights unchanged about 12 hours ago
  • humanizer-12b-q8_2f.cmf
    12 GB
    xet
    Files carry max_tokens=2048 in their sampling defaults (cortiq 0.8.16 serve uses it); weights unchanged about 12 hours ago
  • humanizer-12b-q8_2f.cmf.sha256
    90 Bytes
    Files carry max_tokens=2048 in their sampling defaults (cortiq 0.8.16 serve uses it); weights unchanged about 12 hours ago