Hugging Face's logo

mradermacher
/
35b-beta-long-GGUF

Transformers
GGUF
Inference Endpoints
conversational
Model card Files Community
35b-beta-long-GGUF / README.md
mradermacher's picture
mradermacher
auto-patch README.md
1675906 verified
preview code
|
raw
history blame contribute delete
3.5 kB
metadata
base_model: CausalLM/35b-beta-long
datasets:
  - JosephusCheung/GuanacoDataset
  - meta-math/MetaMathQA
  - jondurbin/airoboros-3.1
  - WizardLM/WizardLM_evol_instruct_V2_196k
  - RyokoAI/ShareGPT52K
  - RyokoAI/Fandom23K
  - milashkaarshif/MoeGirlPedia_wikitext_raw_archive
  - wikipedia
  - wiki_lingua
  - garage-bAInd/Open-Platypus
  - LDJnr/Puffin
  - BAAI/COIG
  - TigerResearch/tigerbot-zhihu-zh-10k
  - liwu/MNBVC
  - teknium/openhermes
  - CausalLM/Refined-Anime-Text
  - microsoft/orca-math-word-problems-200k
  - m-a-p/CodeFeedback-Filtered-Instruction
language:
  - en
  - zh
  - ja
  - de
library_name: transformers
license: wtfpl
quantized_by: mradermacher

About

static quants of https://huggingface.co/CausalLM/35b-beta-long

weighted/imatrix quants are available at https://huggingface.co/mradermacher/35b-beta-long-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 13.9
GGUF Q3_K_S 16.0
GGUF Q3_K_M 17.7 lower quality
GGUF Q3_K_L 19.2
GGUF IQ4_XS 19.4
GGUF Q4_K_S 20.5 fast, recommended
GGUF Q4_K_M 21.6 fast, recommended
GGUF Q5_K_S 24.4
GGUF Q5_K_M 25.1
GGUF Q6_K 28.8 very good quality
GGUF Q8_0 37.3 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.