Poro-34B-i1-GGUF / README.md
mradermacher's picture
auto-patch README.md
6edfbb7 verified
metadata
base_model: LumiOpen/Poro-34B
datasets:
  - cerebras/SlimPajama-627B
  - bigcode/starcoderdata
  - mc4
  - allenai/dolma
language:
  - fi
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher

About

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

static quants are available at https://huggingface.co/mradermacher/Poro-34B-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-IQ1_S 7.9 for the desperate
GGUF i1-IQ1_M 8.6 mostly desperate
GGUF i1-IQ2_XXS 9.7
GGUF i1-IQ2_XS 10.7
GGUF i1-IQ2_S 11.3
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-IQ3_XS 15.2
GGUF i1-IQ3_S 15.6 beats Q3_K*
GGUF i1-Q3_K_S 15.6 IQ3_XS probably better
GGUF i1-IQ3_M 17.2
GGUF i1-Q3_K_M 18.6 IQ3_S probably better
GGUF i1-IQ4_XS 19.1
GGUF i1-Q4_0 20.2 fast, low quality
GGUF i1-Q3_K_L 20.3 IQ3_M probably better
GGUF i1-Q4_K_S 20.3 optimal size/speed/quality
GGUF i1-Q4_K_M 22.5 fast, recommended
GGUF i1-Q5_K_S 24.4
GGUF i1-Q5_K_M 26.2
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.