Virt-io's picture
Update README.md
75c2758 verified
|
raw
history blame
418 Bytes
---
tags:
- gguf
- GGUF
---
# Info
[Thanks to mlabonne for the initial code](https://huggingface.co/mlabonne)
Host files for a google colab notebook, hoping to make it easier to GGUF models with Imatrix.
There are two imatrix datasets, one for general use and one for RP.
After some testing, making the actual quants is really slow, recommended to only use it for the intial FP16 GGUF and imatrix.dat generation.