πŸ“‹ Model Description


base_model: DazzlingXeno/G2-Xeno-SimPO-27b language:
  • en
library_name: transformers quantized_by: mradermacher tags:
  • Story Telling
  • Creative Writing
  • GutenBerg
  • Gemma
  • Prose

About






weighted/imatrix quants of https://huggingface.co/DazzlingXeno/G2-Xeno-SimPO-27b


static quants are available at https://huggingface.co/mradermacher/G2-Xeno-SimPO-27b-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)

LinkTypeSize/GBNotes
GGUFi1-IQ1_S6.2for the desperate
GGUFi1-IQ1_M6.8mostly desperate
GGUFi1-IQ2_XXS7.7
GGUFi1-IQ2_XS8.5
GGUFi1-IQ2_S8.8
GGUFi1-IQ2_M9.5
GGUFi1-Q2K10.5IQ3XXS probably better
GGUFi1-IQ3_XXS10.9lower quality
GGUFi1-IQ3_XS11.7
GGUFi1-IQ3S12.3beats Q3K*
GGUFi1-Q3KS12.3IQ3XS probably better
GGUFi1-IQ3_M12.6
GGUFi1-Q3KM13.5IQ3S probably better
GGUFi1-Q3KL14.6IQ3M probably better
GGUFi1-IQ4_XS14.9
GGUFi1-Q4_015.8fast, low quality
GGUFi1-Q4K_S15.8optimal size/speed/quality
GGUFi1-Q4K_M16.7fast, recommended
GGUFi1-Q5K_S19.0
GGUFi1-Q5K_M19.5
GGUFi1-Q6K22.4practically like static Q6K
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.

πŸ“‚ GGUF File List

πŸ“ Filename πŸ“¦ Size ⚑ Download
G2-Xeno-SimPO-27b.i1-IQ1_M.gguf
LFS
6.23 GB Download
G2-Xeno-SimPO-27b.i1-IQ1_S.gguf
LFS
5.71 GB Download
G2-Xeno-SimPO-27b.i1-IQ2_M.gguf
LFS Q2
8.75 GB Download
G2-Xeno-SimPO-27b.i1-IQ2_S.gguf
LFS Q2
8.06 GB Download
G2-Xeno-SimPO-27b.i1-IQ2_XS.gguf
LFS Q2
7.82 GB Download
G2-Xeno-SimPO-27b.i1-IQ2_XXS.gguf
LFS Q2
7.1 GB Download
G2-Xeno-SimPO-27b.i1-IQ3_M.gguf
LFS Q3
11.6 GB Download
G2-Xeno-SimPO-27b.i1-IQ3_S.gguf
LFS Q3
11.33 GB Download
G2-Xeno-SimPO-27b.i1-IQ3_XS.gguf
LFS Q3
10.76 GB Download
G2-Xeno-SimPO-27b.i1-IQ3_XXS.gguf
LFS Q3
10.01 GB Download
G2-Xeno-SimPO-27b.i1-IQ4_XS.gguf
LFS Q4
13.8 GB Download
G2-Xeno-SimPO-27b.i1-Q2_K.gguf
LFS Q2
9.73 GB Download
G2-Xeno-SimPO-27b.i1-Q3_K_L.gguf
LFS Q3
13.52 GB Download
G2-Xeno-SimPO-27b.i1-Q3_K_M.gguf
LFS Q3
12.5 GB Download
G2-Xeno-SimPO-27b.i1-Q3_K_S.gguf
LFS Q3
11.33 GB Download
G2-Xeno-SimPO-27b.i1-Q4_0.gguf
Recommended LFS Q4
14.6 GB Download
G2-Xeno-SimPO-27b.i1-Q4_K_M.gguf
LFS Q4
15.5 GB Download
G2-Xeno-SimPO-27b.i1-Q4_K_S.gguf
LFS Q4
14.66 GB Download
G2-Xeno-SimPO-27b.i1-Q5_K_M.gguf
LFS Q5
18.08 GB Download
G2-Xeno-SimPO-27b.i1-Q5_K_S.gguf
LFS Q5
17.59 GB Download
G2-Xeno-SimPO-27b.i1-Q6_K.gguf
LFS Q6
20.81 GB Download