Hugging Face's logo

mradermacher
/
HelpingAI-Lite-1.5T-i1-GGUF

Transformers
GGUF
English
Text-Generation
Transformers
HelpingAI
Inference Endpoints
imatrix
Model card Files Community
HelpingAI-Lite-1.5T-i1-GGUF / README.md
mradermacher's picture
mradermacher
auto-patch README.md
70ce5ba verified
preview code
|
raw
history blame contribute delete
5.53 kB
metadata
base_model: OEvortex/HelpingAI-Lite-1.5T
datasets:
  - cerebras/SlimPajama-627B
  - HuggingFaceH4/ultrachat_200k
  - bigcode/starcoderdata
  - HuggingFaceH4/ultrafeedback_binarized
  - OEvortex/vortex-mini
  - Open-Orca/OpenOrca
language:
  - en
library_name: transformers
license: other
license_link: https://huggingface.co/OEvortex/vortex-3b/raw/main/LICENSE.md
license_name: hsul
quantized_by: mradermacher
tags:
  - Text-Generation
  - Transformers
  - HelpingAI

About

weighted/imatrix quants of https://huggingface.co/OEvortex/HelpingAI-Lite-1.5T

static quants are available at https://huggingface.co/mradermacher/HelpingAI-Lite-1.5T-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 0.4 for the desperate
GGUF i1-IQ1_M 0.4 mostly desperate
GGUF i1-IQ2_XXS 0.4
GGUF i1-IQ2_XS 0.5
GGUF i1-IQ2_S 0.5
GGUF i1-IQ2_M 0.5
GGUF i1-Q2_K_S 0.5 very low quality
GGUF i1-Q2_K 0.5 IQ3_XXS probably better
GGUF i1-IQ3_XXS 0.5 lower quality
GGUF i1-IQ3_XS 0.6
GGUF i1-Q3_K_S 0.6 IQ3_XS probably better
GGUF i1-IQ3_S 0.6 beats Q3_K*
GGUF i1-IQ3_M 0.6
GGUF i1-Q3_K_M 0.6 IQ3_S probably better
GGUF i1-Q3_K_L 0.7 IQ3_M probably better
GGUF i1-IQ4_XS 0.7
GGUF i1-Q4_0 0.7 fast, low quality
GGUF i1-Q4_K_S 0.7 optimal size/speed/quality
GGUF i1-Q4_K_M 0.8 fast, recommended
GGUF i1-Q5_K_S 0.9
GGUF i1-Q5_K_M 0.9
GGUF i1-Q6_K 1.0 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.