Hugging Face's logo

mradermacher
/
maid-yuzu-v7-GGUF

Transformers
GGUF
English
mergekit
Merge
Inference Endpoints
Model card Files Community
maid-yuzu-v7-GGUF / README.md
mradermacher's picture
mradermacher
auto-patch README.md
0324868 verified
preview code
|
raw
history blame
2.65 kB
metadata
base_model:
  - ycros/BagelMIsteryTour-v2-8x7B
  - smelborp/MixtralOrochi8x7B
  - cognitivecomputations/dolphin-2.7-mixtral-8x7b
language:
  - en
library_name: transformers
quantized_by: mradermacher
tags:
  - mergekit
  - merge

About

static quants of https://huggingface.co/rhplus0831/maid-yuzu-v7

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF Q2_K 17.6
GGUF Q3_K_S 20.7
GGUF Q3_K_M 22.8 lower quality
GGUF Q3_K_L 24.4
GGUF Q4_K_S 27.0 fast, medium quality
GGUF Q4_K_M 28.7 fast, medium quality
GGUF Q5_K_S 32.5
GGUF Q5_K_M 33.5
GGUF Q6_K 38.6 very good quality
PART 1 PART 2 Q8_0 49.8 fast, best quality

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.