mradermacher's picture
auto-patch README.md
94a223c verified
metadata
base_model: NousResearch/Nous-Hermes-Llama2-70b
language:
  - en
library_name: transformers
license:
  - mit
quantized_by: mradermacher
tags:
  - llama-2
  - self-instruct
  - distillation
  - synthetic instruction

About

static quants of https://huggingface.co/NousResearch/Nous-Hermes-Llama2-70b

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-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 25.6
GGUF IQ3_XS 28.4
GGUF IQ3_S 30.0 beats Q3_K*
GGUF Q3_K_S 30.0
GGUF IQ3_M 31.0
GGUF Q3_K_M 33.4 lower quality
GGUF Q3_K_L 36.2
GGUF IQ4_XS 37.3
GGUF Q4_K_S 39.3 fast, recommended
GGUF Q4_K_M 41.5 fast, recommended
GGUF Q5_K_S 47.6
GGUF Q5_K_M 48.9
PART 1 PART 2 Q6_K 56.7 very good quality
PART 1 PART 2 Q8_0 73.4 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.