base_model: mlabonne/Beyonder-4x7B-v2
language:
- en
library_name: transformers
license: other
license_link: https://huggingface.co/WizardLM/WizardMath-7B-V1.1/resolve/main/LICENSE
license_name: microsoft-research-license
quantized_by: mradermacher
tags:
- moe
- merge
- mergekit
- Mistral
- openchat/openchat-3.5-1210
- beowolx/CodeNinja-1.0-OpenChat-7B
- maywell/PiVoT-0.1-Starling-LM-RP
- WizardLM/WizardMath-7B-V1.1
About
static quants of https://huggingface.co/mlabonne/Beyonder-4x7B-v2
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Beyonder-4x7B-v2-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 | 9.1 | |
| GGUF | IQ3_XS | 10.1 | |
| GGUF | Q3_K_S | 10.7 | |
| GGUF | IQ3_S | 10.7 | beats Q3_K* |
| GGUF | IQ3_M | 10.9 | |
| GGUF | Q3_K_M | 11.8 | lower quality |
| GGUF | Q3_K_L | 12.8 | |
| GGUF | IQ4_XS | 13.3 | |
| GGUF | Q4_K_S | 14.0 | fast, recommended |
| GGUF | Q4_K_M | 14.9 | fast, recommended |
| GGUF | Q5_K_S | 16.9 | |
| GGUF | Q5_K_M | 17.4 | |
| GGUF | Q6_K | 20.1 | very good quality |
| GGUF | Q8_0 | 25.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
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.