mradermacher's picture
auto-patch README.md
0af3df8 verified
|
raw
history blame
4 kB
metadata
base_model: 152334H/miqu-1-70b-sf
datasets:
  - abacusai/SystemChat
exported_from: abideen/Liberated-Miqu-70B
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - Miqu
  - Liberated
  - Uncensored
  - 70B

About

static quants of https://huggingface.co/abideen/Liberated-Miqu-70B

weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.

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 25.9
GGUF IQ3_XS 28.7
GGUF IQ3_S 30.3 beats Q3_K*
GGUF Q3_K_S 30.3
GGUF IQ3_M 31.4
GGUF Q3_K_M 33.7 lower quality
GGUF Q3_K_L 36.6
GGUF IQ4_XS 37.6
GGUF Q4_0 39.3
GGUF IQ4_NL 39.7 slightly worse than Q4_K_S
GGUF Q4_K_S 39.7 fast, recommended
GGUF Q4_K_M 41.8 fast, recommended
GGUF Q5_K_S 47.9
GGUF Q5_K_M 49.2
PART 1 PART 2 Q6_K 57.0 very good quality
PART 1 PART 2 Q8_0 73.6 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.