mradermacher's picture
auto-patch README.md
553aeb1 verified
metadata
base_model: sambanovasystems/SambaLingo-Slovenian-Base
datasets:
  - uonlp/CulturaX
language:
  - sl
  - en
library_name: transformers
license: llama2
quantized_by: mradermacher

About

static quants of https://huggingface.co/sambanovasystems/SambaLingo-Slovenian-Base

weighted/imatrix quants are available at https://huggingface.co/mradermacher/SambaLingo-Slovenian-Base-i1-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 Q2_K 2.8
GGUF Q3_K_S 3.2
GGUF Q3_K_M 3.5 lower quality
GGUF Q3_K_L 3.8
GGUF IQ4_XS 3.9
GGUF Q4_0_4_4 4.1 fast on arm, low quality
GGUF Q4_K_S 4.1 fast, recommended
GGUF Q4_K_M 4.3 fast, recommended
GGUF Q5_K_S 4.9
GGUF Q5_K_M 5.0
GGUF Q6_K 5.8 very good quality
GGUF Q8_0 7.5 fast, best quality
GGUF f16 14.0 16 bpw, overkill

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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.