Pyrhea-72B-i1-GGUF / README.md
mradermacher's picture
auto-patch README.md
3ecbb3b verified
|
raw
history blame
3.18 kB
metadata
base_model:
  - davidkim205/Rhea-72b-v0.5
  - abacusai/Smaug-72B-v0.1
exported_from: saucam/Pyrhea-72B
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - merge
  - mergekit
  - davidkim205/Rhea-72b-v0.5
  - abacusai/Smaug-72B-v0.1

About

weighted/imatrix quants of https://huggingface.co/saucam/Pyrhea-72B

static quants are available at https://huggingface.co/mradermacher/Pyrhea-72B-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-IQ2_M 25.3
GGUF i1-Q2_K 27.2 IQ3_XXS probably better
GGUF i1-IQ3_XXS 27.8 lower quality
GGUF i1-Q3_K_S 31.7 IQ3_XS probably better
GGUF i1-Q3_K_M 35.4 IQ3_S probably better
GGUF i1-Q3_K_L 38.6 IQ3_M probably better
GGUF i1-IQ4_XS 38.9
GGUF i1-Q4_K_S 41.4 optimal size/speed/quality
GGUF i1-Q4_K_M 43.9 fast, recommended
GGUF i1-Q5_K_S 50.0
PART 1 PART 2 i1-Q6_K 59.4 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

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.