mradermacher's picture
auto-patch README.md
521c749 verified
metadata
base_model: cloudyu/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B
language:
  - en
library_name: transformers
license: mit
quantized_by: mradermacher
tags:
  - moe
  - DPO
  - RL-TUNED

About

static quants of https://huggingface.co/cloudyu/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B-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 22.5
GGUF IQ3_XS 25.1
GGUF Q3_K_S 26.4
GGUF IQ3_S 26.5 beats Q3_K*
GGUF IQ3_M 27.2
GGUF Q3_K_M 29.3 lower quality
GGUF Q3_K_L 31.9
GGUF IQ4_XS 32.9
GGUF Q4_K_S 34.7 fast, recommended
GGUF Q4_K_M 36.8 fast, recommended
GGUF Q5_K_S 42.0
GGUF Q5_K_M 43.2
GGUF Q6_K 50.0 very good quality
PART 1 PART 2 Q8_0 64.7 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.