CoolFace
Modelpublic

mradermacher/TinyLlama_v1.1_math_code-i1-GGUF

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes707downloads
Model Card

About

<!-- ### quantizeversion: 2 --> <!-- ### outputtensorquantised: 1 --> <!-- ### converttype: hf --> <!-- ### vocabtype: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/TinyLlama/TinyLlamav1.1mathcode

<!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/TinyLlamav1.1math_code-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_S0.4for the desperate
GGUFi1-IQ1_M0.4mostly desperate
GGUFi1-IQ2_XXS0.4
GGUFi1-IQ2_XS0.5
GGUFi1-IQ2_S0.5
GGUFi1-IQ2_M0.5
GGUFi1-Q2KS0.5very low quality
GGUFi1-Q2_K0.5IQ3_XXS probably better
GGUFi1-IQ3_XXS0.5lower quality
GGUFi1-IQ3_XS0.6
GGUFi1-Q3KS0.6IQ3_XS probably better
GGUFi1-IQ3_S0.6beats Q3_K*
GGUFi1-IQ3_M0.6
GGUFi1-Q3KM0.6IQ3_S probably better
GGUFi1-Q3KL0.7IQ3_M probably better
GGUFi1-IQ4_XS0.7
GGUFi1-IQ4_NL0.7prefer IQ4_XS
GGUFi1-Q4_00.7fast, low quality
GGUFi1-Q4KS0.7optimal size/speed/quality
GGUFi1-Q4KM0.8fast, recommended
GGUFi1-Q4_10.8
GGUFi1-Q5KS0.9
GGUFi1-Q5KM0.9
GGUFi1-Q6_K1.0practically 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 -->