mradermacher's picture
auto-patch README.md
b2449a9 verified
|
raw
history blame
6.36 kB
metadata
base_model: sophosympatheia/Aurora-Nights-103B-v1.0
language:
  - en
library_name: transformers
license: llama2
quantized_by: mradermacher

About

weighted/imatrix wants of https://huggingface.co/sophosympatheia/Aurora-Nights-103B-v1.0

the weights were calculated using 164k semi-random english-only tokens.

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 22.1 for the desperate
GGUF i1-IQ1_M 23.9 mostly desperate
GGUF i1-IQ2_XXS 27.7
GGUF i1-IQ2_XS 30.8
GGUF i1-IQ2_S 32.3
GGUF i1-IQ2_M 35.1
GGUF i1-Q2_K 38.3 IQ3_XXS probably better
GGUF i1-IQ3_XXS 40.6 lower quality
GGUF i1-Q3_K_XS 42.4
GGUF i1-IQ3_XS 42.5
GGUF i1-Q3_K_S 44.9 IQ3_XS probably better
GGUF i1-IQ3_S 45.0 beats Q3_K*
GGUF i1-IQ3_M 46.5
PART 1 PART 2 i1-Q3_K_M 50.0 IQ3_S probably better
PART 1 PART 2 i1-Q3_K_L 54.5 IQ3_M probably better
PART 1 PART 2 i1-IQ4_XS 55.5
PART 1 PART 2 i1-Q4_0 58.4 fast, low quality
PART 1 PART 2 i1-Q4_K_S 59.0 optimal size/speed/quality
PART 1 PART 2 i1-Q4_K_M 62.3 fast, recommended
PART 1 PART 2 i1-Q5_K_S 71.4
PART 1 PART 2 i1-Q5_K_M 73.3
PART 1 PART 2 i1-Q6_K 85.1 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.