mradermacher's picture
auto-patch README.md
f4327cd verified
metadata
base_model: mlinmg/SG-Raccoon-Yi-55B-200k
language:
  - en,
library_name: transformers
license: other
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
license_name: yi-license
quantized_by: mradermacher

About

weighted/imatrix quants of https://huggingface.co/mlinmg/SG-Raccoon-Yi-55B-200k

static quants are available at https://huggingface.co/mradermacher/SG-Raccoon-Yi-55B-200k-GGUF

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 i1-IQ1_S 12.1 for the desperate
GGUF i1-IQ1_M 13.2 mostly desperate
GGUF i1-IQ2_XXS 15.0
GGUF i1-IQ2_XS 16.6
GGUF i1-IQ2_S 17.6
GGUF i1-IQ2_M 19.0
GGUF i1-Q2_K 20.7 IQ3_XXS probably better
GGUF i1-IQ3_XXS 21.6 lower quality
GGUF i1-IQ3_XS 23.0
GGUF i1-Q3_K_S 24.2 IQ3_XS probably better
GGUF i1-IQ3_S 24.3 beats Q3_K*
GGUF i1-IQ3_M 25.2
GGUF i1-Q3_K_M 27.0 IQ3_S probably better
GGUF i1-Q3_K_L 29.4 IQ3_M probably better
GGUF i1-IQ4_XS 29.9
GGUF i1-Q4_0 31.6 fast, low quality
GGUF i1-Q4_K_S 31.7 optimal size/speed/quality
GGUF i1-Q4_K_M 33.4 fast, recommended
GGUF i1-Q5_K_S 38.4
GGUF i1-Q5_K_M 39.4
GGUF i1-Q6_K 45.7 practically like static Q6_K

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

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

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.