Hugging Face's logo

mradermacher
/
japanese-stablelm-3b-4e1t-base-GGUF

Transformers
GGUF
Japanese
japanese-stablelm
causal-lm
Inference Endpoints
Model card Files Community
japanese-stablelm-3b-4e1t-base-GGUF / README.md
mradermacher's picture
mradermacher
auto-patch README.md
0e515cc verified
preview code
|
raw
history blame contribute delete
4.16 kB
metadata
base_model: stabilityai/japanese-stablelm-3b-4e1t-base
datasets:
  - wikipedia
  - mc4
  - cc100
  - oscar-corpus/OSCAR-2301
  - oscar-corpus/OSCAR-2201
  - cerebras/SlimPajama-627B
extra_gated_fields:
  Country: text
  Email: text
  I allow Stability AI to contact me about information related to its models and research: checkbox
  Name: text
  Organization or Affiliation: text
language:
  - ja
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - japanese-stablelm
  - causal-lm

About

static quants of https://huggingface.co/stabilityai/japanese-stablelm-3b-4e1t-base

weighted/imatrix quants are available at https://huggingface.co/mradermacher/japanese-stablelm-3b-4e1t-base-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 1.2
GGUF Q3_K_S 1.4
GGUF Q3_K_M 1.5 lower quality
GGUF Q3_K_L 1.6
GGUF IQ4_XS 1.6
GGUF Q4_K_S 1.7 fast, recommended
GGUF Q4_K_M 1.8 fast, recommended
GGUF Q5_K_S 2.0
GGUF Q5_K_M 2.1
GGUF Q6_K 2.4 very good quality
GGUF Q8_0 3.1 fast, best quality
GGUF f16 5.7 16 bpw, overkill

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 private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.