mradermacher's picture
auto-patch README.md
49e4aec verified
metadata
base_model: cloudyu/Mixtral_7Bx5_MoE_30B_DPO
language:
  - en
library_name: transformers
license: mit
no_imatrix: >-
  Missing importance matrix for tensor blk.9.ffn_gate_exps.weight in a very
  low-bit quantization
quantized_by: mradermacher
tags:
  - moe

About

static quants of https://huggingface.co/cloudyu/Mixtral_7Bx5_MoE_30B_DPO

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 11.0
GGUF IQ3_XS 12.3
GGUF Q3_K_S 13.0
GGUF IQ3_S 13.0 beats Q3_K*
GGUF IQ3_M 13.2
GGUF Q3_K_M 14.4 lower quality
GGUF Q3_K_L 15.6
GGUF IQ4_XS 16.2
GGUF Q4_K_S 17.0 fast, recommended
GGUF Q4_K_M 18.1 fast, recommended
GGUF Q5_K_S 20.6
GGUF Q5_K_M 21.2
GGUF Q6_K 24.5 very good quality
GGUF Q8_0 31.8 fast, best quality

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.