Hugging Face's logo

mradermacher
/
NinjaMouse-2.4B-32L-danube-GGUF

Transformers
GGUF
English
code
Inference Endpoints
conversational
Model card Files Community
NinjaMouse-2.4B-32L-danube-GGUF / README.md
mradermacher's picture
mradermacher
auto-patch README.md
dd5023d verified
preview code
|
raw
history blame contribute delete
4.29 kB
metadata
base_model: trollek/NinjaMouse-2.4B-32L-danube
datasets:
  - m-a-p/Code-Feedback
  - HuggingFaceTB/cosmopedia-100k
  - LDJnr/Capybara
  - vicgalle/alpaca-gpt4
  - glaiveai/glaive-code-assistant-v2
  - WhiteRabbitNeo/WRN-Chapter-1
  - WhiteRabbitNeo/WRN-Chapter-2
  - m-a-p/CodeFeedback-Filtered-Instruction
  - jondurbin/airoboros-3.2
  - euclaise/WritingPrompts_curated
  - derek-thomas/squad-v1.1-t5-question-generation
  - reinforz/question_generation_data
  - teknium/GPTeacher-General-Instruct
  - dim/roleplay_instruct_v2_final
  - TIGER-Lab/MathInstruct
  - abacusai/SystemChat
  - Mihaiii/OpenHermes-2.5-1k-longest-curated
language:
  - en
library_name: transformers
license: apache-2.0
license_link: LICENSE
license_name: a
quantized_by: mradermacher
tags:
  - code

About

static quants of https://huggingface.co/trollek/NinjaMouse-2.4B-32L-danube

weighted/imatrix quants are available at https://huggingface.co/mradermacher/NinjaMouse-2.4B-32L-danube-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 1.0
GGUF Q3_K_S 1.2
GGUF Q3_K_M 1.3 lower quality
GGUF Q3_K_L 1.4
GGUF IQ4_XS 1.4
GGUF Q4_K_S 1.5 fast, recommended
GGUF Q4_K_M 1.5 fast, recommended
GGUF Q5_K_S 1.8
GGUF Q5_K_M 1.8
GGUF Q6_K 2.1 very good quality
GGUF Q8_0 2.6 fast, best quality
GGUF f16 4.9 16 bpw, overkill

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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.