CoolFace
Modelpublic

mradermacher/jais-family-2p7b-i1-GGUF

sourceHugging Faceapache-2.0updated 26d agoView on Hugging Face
0likes1.3kdownloads
Model Card

About

<!-- ### quantizeversion: 2 --> <!-- ### outputtensorquantised: 1 --> <!-- ### converttype: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/inception42/jais-family-2p7b

<!-- provided-files -->

*For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#jais-family-2p7b-i1-GGUF).*

static quants are available at https://huggingface.co/mradermacher/jais-family-2p7b-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_S1.8for the desperate
GGUFi1-IQ1_M1.9mostly desperate
GGUFi1-IQ2_XXS2.0
GGUFi1-IQ2_XS2.0
GGUFi1-IQ2_S2.1
GGUFi1-Q2KS2.1very low quality
GGUFi1-IQ2_M2.1
GGUFi1-Q2_K2.1IQ3_XXS probably better
GGUFi1-IQ3_XXS2.2lower quality
GGUFi1-IQ3_XS2.3
GGUFi1-IQ3_S2.3beats Q3_K*
GGUFi1-Q3KS2.3IQ3_XS probably better
GGUFi1-IQ3_M2.5
GGUFi1-Q3KM2.5IQ3_S probably better
GGUFi1-Q3KL2.5IQ3_M probably better
GGUFi1-IQ4_XS2.6
GGUFi1-Q4KS2.6optimal size/speed/quality
GGUFi1-Q4KM2.7fast, recommended
GGUFi1-Q5KS2.9
GGUFi1-Q5KM3.0
GGUFi1-Q6_K3.2practically 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. 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.

<!-- end -->