mradermacher's picture
auto-patch README.md
caa3b9c verified
|
raw
history blame
2.81 kB
metadata
base_model: LumiOpen/Poro-34B-chat
datasets:
  - LumiOpen/instruction-collection-fin
language:
  - fi
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher

About

weighted/imatrix quants of https://huggingface.co/LumiOpen/Poro-34B-chat

static quants are available at https://huggingface.co/mradermacher/Poro-34B-chat-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 12.3
GGUF i1-Q2_K 13.5 IQ3_XXS probably better
GGUF i1-IQ3_XXS 14.0 lower quality
GGUF i1-Q3_K_M 18.6 IQ3_S probably better
GGUF i1-Q4_K_S 20.3 optimal size/speed/quality
GGUF i1-Q4_K_M 22.5 fast, recommended
GGUF i1-Q6_K 28.9 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. Additional thanks to @nicoboss for giving me access to his hardware for calculating the imatrix for these quants.