Hugging Face's logo

mradermacher
/
Apollo2-3.8B-GGUF

Transformers
GGUF
biology
medical
Inference Endpoints
conversational
Model card Files Community
Apollo2-3.8B-GGUF / README.md
mradermacher's picture
mradermacher
auto-patch README.md
4e48bf1 verified
preview code
|
raw
history blame contribute delete
3.63 kB
metadata
base_model: FreedomIntelligence/Apollo2-3.8B
datasets:
  - FreedomIntelligence/ApolloMoEDataset
language:
  - ar
  - en
  - zh
  - ko
  - ja
  - mn
  - th
  - vi
  - lo
  - mg
  - de
  - pt
  - es
  - fr
  - ru
  - it
  - hr
  - gl
  - cs
  - co
  - la
  - uk
  - bs
  - bg
  - eo
  - sq
  - da
  - sa
  - gn
  - sr
  - sk
  - gd
  - lb
  - hi
  - ku
  - mt
  - he
  - ln
  - bm
  - sw
  - ig
  - rw
  - ha
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - biology
  - medical

About

static quants of https://huggingface.co/FreedomIntelligence/Apollo2-3.8B

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Apollo2-3.8B-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 1.5
GGUF Q3_K_S 1.8
GGUF Q3_K_M 2.1 lower quality
GGUF IQ4_XS 2.2
GGUF Q3_K_L 2.2
GGUF Q4_K_S 2.3 fast, recommended
GGUF Q4_K_M 2.5 fast, recommended
GGUF Q5_K_S 2.7
GGUF Q5_K_M 2.9
GGUF Q6_K 3.2 very good quality
GGUF Q8_0 4.2 fast, best quality
GGUF f16 7.7 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.