Hugging Face's logo

mradermacher
/
Babel-83B-Chat-i1-GGUF

Transformers
GGUF
multilingual
babel
Inference Endpoints
imatrix
conversational
Model card Files Community
Babel-83B-Chat-i1-GGUF / README.md
mradermacher's picture
mradermacher
auto-patch README.md
8999086 verified
preview code
|
raw
history blame
4.37 kB
metadata
base_model: Tower-Babel/Babel-83B-Chat
language:
  - en
  - zh
  - hi
  - es
  - fr
  - ar
  - bn
  - ru
  - pt
  - id
  - ur
  - de
  - ja
  - sw
  - ta
  - tr
  - ko
  - vi
  - jv
  - it
  - ha
  - th
  - fa
  - tl
  - my
library_name: transformers
license: other
license_link: https://huggingface.co./SeaLLMs/SeaLLM-13B-Chat/blob/main/LICENSE
license_name: seallm
quantized_by: mradermacher
tags:
  - multilingual
  - babel

About

weighted/imatrix quants of https://huggingface.co./Tower-Babel/Babel-83B-Chat

static quants are available at https://huggingface.co./mradermacher/Babel-83B-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-IQ1_M 27.2 mostly desperate
GGUF i1-IQ2_XXS 29.2
GGUF i1-IQ2_M 33.6
GGUF i1-Q2_K_S 33.8 very low quality
GGUF i1-Q2_K 34.1 IQ3_XXS probably better
GGUF i1-IQ3_XXS 36.4 lower quality
GGUF i1-Q3_K_S 39.3 IQ3_XS probably better
GGUF i1-IQ3_M 40.6
GGUF i1-Q3_K_M 43.1 IQ3_S probably better
GGUF i1-IQ4_XS 45.5
PART 1 PART 2 i1-Q4_K_S 50.2 optimal size/speed/quality
PART 1 PART 2 i1-Q4_K_M 54.3 fast, recommended
PART 1 PART 2 i1-Q6_K 73.8 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 private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.