mradermacher's picture
auto-patch README.md
e659520 verified
metadata
base_model: codellama/CodeLlama-13b-hf
language:
  - code
library_name: transformers
license: llama2
quantized_by: mradermacher
tags:
  - llama-2

About

static quants of https://huggingface.co/codellama/CodeLlama-13b-hf

weighted/imatrix quants are available at https://huggingface.co/mradermacher/CodeLlama-13b-hf-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 5.0
GGUF IQ3_XS 5.5
GGUF IQ3_S 5.8 beats Q3_K*
GGUF Q3_K_S 5.8
GGUF IQ3_M 6.1
GGUF Q3_K_M 6.4 lower quality
GGUF Q3_K_L 7.0
GGUF IQ4_XS 7.1
GGUF Q4_K_S 7.5 fast, recommended
GGUF Q4_K_M 8.0 fast, recommended
GGUF Q5_K_S 9.1
GGUF Q5_K_M 9.3
GGUF Q6_K 10.8 very good quality
GGUF Q8_0 13.9 fast, best quality

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.