mradermacher's picture
auto-patch README.md
57b5950 verified
metadata
base_model: ludis/tsukasa-120b-qlora
datasets:
  - PygmalionAI/PIPPA
  - lemonilia/LimaRP
language:
  - en
library_name: transformers
quantized_by: mradermacher

About

static quants of https://huggingface.co/ludis/tsukasa-120b-qlora

weighted/imatrix quants are available at https://huggingface.co/mradermacher/tsukasa-120b-qlora-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 43.3
GGUF IQ3_XS 48.2
PART 1 PART 2 Q3_K_S 50.8
PART 1 PART 2 IQ3_S 51.0 beats Q3_K*
PART 1 PART 2 IQ3_M 52.7
PART 1 PART 2 Q3_K_M 56.7 lower quality
PART 1 PART 2 Q3_K_L 61.8
PART 1 PART 2 IQ4_XS 63.5
PART 1 PART 2 Q4_K_S 66.9 fast, recommended
PART 1 PART 2 Q4_K_M 70.7 fast, recommended
PART 1 PART 2 Q5_K_S 81.1
PART 1 PART 2 Q5_K_M 83.3
PART 1 PART 2 Q6_K 96.7 very good quality
PART 1 PART 2 PART 3 Q8_0 125.2 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.