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

infosave
/
Hy4-flash-cmf

Text Generation
cortiq
English
Chinese
Russian
cmf
quantized
q4tp
q2tp
vulkan
Mixture of Experts
engram
hunyuan
hy4-flash
cuda
Model card Files Files and versions
xet
Community

Instructions to use infosave/Hy4-flash-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • cortiq

    How to use infosave/Hy4-flash-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/Hy4-flash-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
Hy4-flash-cmf / assets
169 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 12 commits
infosave's picture
infosave
Add assets/perf_cuda_zh.png
50dcb2b verified 1 day ago
  • perf_cuda_en.png
    53.7 kB
    Add assets/perf_cuda_en.png 1 day ago
  • perf_cuda_ru.png
    53.5 kB
    Add assets/perf_cuda_ru.png 1 day ago
  • perf_cuda_zh.png
    62 kB
    Add assets/perf_cuda_zh.png 1 day ago