mradermacher's picture
Upload README.md with huggingface_hub
ad636bc verified
|
raw
history blame
2.64 kB
metadata
language:
  - en
library_name: transformers
license: llama2
quantized_by: mradermacher

About

weighted/imatrix quants of https://huggingface.co/sophosympatheia/Aurora-Nights-70B-v1.0

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 14.9
GGUF i1-IQ2_XXS 18.6
GGUF i1-IQ2_XS 20.7
GGUF i1-Q2_K 25.8 IQ3_XXS probably better
GGUF i1-IQ3_XXS 27.3 fast, lower quality
GGUF i1-Q3_K_XS 28.6
GGUF i1-Q3_K_S 30.2 IQ3_XS probably better
GGUF i1-Q3_K_M 33.6 IQ3_S probably better
GGUF i1-Q3_K_L 36.5 IQ3_M probably better
GGUF i1-Q4_K_S 39.6 almost as good as Q4_K_M
GGUF i1-Q4_K_M 41.7 fast, medium quality

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png