Text Generation
cortiq
English
Russian
Chinese
cmf
quantized
q4tp
Mixture of Experts
code
expert-pruning
cuda
hy4-flash
Instructions to use infosave/Hy4-flash-Fast-Code-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/Hy4-flash-Fast-Code-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-Fast-Code-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
Commit History
2 days ago
-
cortiq 0.9.8: the q4 file (dense trunk at 4 bits), speeds, card
Verified signaturec2a83d5 -
Upload hy4-flash-fast-code-q4.cmf with huggingface_hub
Verified signature4efccf5
3 days ago
-
Card (EN/RU/ZH), figures, license, sha256
Verified signature3bd12dd -
Upload hy4-flash-fast-code.cmf with huggingface_hub
Verified signature9307826 -
initial commit
Verified signature1affb41