brucethemoose's picture
Update README.md
ff0925e verified
|
raw
history blame
556 Bytes
---
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
language:
- en
library_name: transformers
base_model: []
tags:
- mergekit
- merge
- Yi
- gguf
---
See the main model card: https://huggingface.co/brucethemoose/Yi-34B-200K-RPMerge
Experimental imatrix quantizations, at 16K context, using a cocktail of data taken from the exllamav2 repo, kalomaze's random token tests and some stories.
Consider them experimental! But they may be better than the equivalent non-matrix GGUFs. Or they may not!