Transformers
GGUF
English
Inference Endpoints
imatrix
mradermacher's picture
auto-patch README.md
737729f verified
metadata
base_model: cognitivecomputations/WizardLM-1.0-Uncensored-Llama2-13b
datasets:
  - ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
language:
  - en
library_name: transformers
license: llama2
quantized_by: mradermacher

About

weighted/imatrix quants of https://huggingface.co/cognitivecomputations/WizardLM-1.0-Uncensored-Llama2-13b

static quants are available at https://huggingface.co/mradermacher/WizardLM-1.0-Uncensored-Llama2-13b-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 3.0 for the desperate
GGUF i1-IQ1_M 3.2 mostly desperate
GGUF i1-IQ2_XXS 3.6
GGUF i1-IQ2_XS 4.0
GGUF i1-IQ2_S 4.3
GGUF i1-IQ2_M 4.6
GGUF i1-Q2_K 5.0 IQ3_XXS probably better
GGUF i1-IQ3_XXS 5.1 lower quality
GGUF i1-IQ3_XS 5.5
GGUF i1-IQ3_S 5.8 beats Q3_K*
GGUF i1-Q3_K_S 5.8 IQ3_XS probably better
GGUF i1-IQ3_M 6.1
GGUF i1-Q3_K_M 6.4 IQ3_S probably better
GGUF i1-Q3_K_L 7.0 IQ3_M probably better
GGUF i1-IQ4_XS 7.1
GGUF i1-Q4_0 7.5 fast, low quality
GGUF i1-Q4_K_S 7.5 optimal size/speed/quality
GGUF i1-Q4_K_M 8.0 fast, recommended
GGUF i1-Q5_K_S 9.1
GGUF i1-Q5_K_M 9.3
GGUF i1-Q6_K 10.8 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. 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.