mradermacher/SpyazWeb_AI_DeepMind_Project-i1-GGUF

---

basemodel: LeroyDyer/SpyazWebAIDeepMindProject datasets:

• gretelai/synthetictexttosql
• HuggingFaceTB/cosmopedia
• teknium/OpenHermes-2.5
• Open-Orca/SlimOrca
• Open-Orca/OpenOrca
• cognitivecomputations/dolphin-coder
• databricks/databricks-dolly-15k
• yahma/alpaca-cleaned
• uonlp/CulturaX
• mwitiderrick/SwahiliPlatypus
• swahili
• Rogendo/English-Swahili-Sentence-Pairs
• ise-uiuc/Magicoder-Evol-Instruct-110K
• meta-math/MetaMathQA
• abacusai/ARCDPOFewShot
• abacusai/MetaMathDPOFewShot
• abacusai/HellaSwagDPOFewShot
• HaltiaAI/Her-The-Movie-Samantha-and-Theodore-Dataset
• gretelai/synthetictexttosql
• HuggingFaceTB/cosmopedia
• teknium/OpenHermes-2.5
• cognitivecomputations/dolphin-coder
• databricks/databricks-dolly-15k
• yahma/alpaca-cleaned
• uonlp/CulturaX
• mwitiderrick/SwahiliPlatypus
• swahili
• Rogendo/English-Swahili-Sentence-Pairs
• ise-uiuc/Magicoder-Evol-Instruct-110K
• meta-math/MetaMathQA

language:

• en

library_name: transformers license: apache-2.0 quantized_by: mradermacher tags:

• text-generation-inference
• transformers
• leaderboard
• mistral
• trl

---

About

weighted/imatrix quants of https://huggingface.co/LeroyDyer/SpyazWebAIDeepMind_Project

static quants are available at https://huggingface.co/mradermacher/SpyazWebAIDeepMind_Project-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	i1-IQ1_S	1.7	for the desperate
GGUF	i1-IQ1_M	1.9	mostly desperate
GGUF	i1-IQ2_XXS	2.1
GGUF	i1-IQ2_XS	2.3
GGUF	i1-IQ2_S	2.4
GGUF	i1-IQ2_M	2.6
GGUF	i1-Q2K_S	2.6	very low quality
GGUF	i1-Q2K	2.8	IQ3XXS probably better
GGUF	i1-IQ3_XXS	2.9	lower quality
GGUF	i1-IQ3_XS	3.1
GGUF	i1-Q3KS	3.3	IQ3XS probably better
GGUF	i1-IQ3S	3.3	beats Q3K*
GGUF	i1-IQ3_M	3.4
GGUF	i1-Q3KM	3.6	IQ3S probably better
GGUF	i1-Q3KL	3.9	IQ3M probably better
GGUF	i1-IQ4_XS	4.0
GGUF	i1-Q4_0	4.2	fast, low quality
GGUF	i1-IQ4NL	4.2	prefer IQ4XS
GGUF	i1-Q4K_S	4.2	optimal size/speed/quality
GGUF	i1-Q4K_M	4.5	fast, recommended
GGUF	i1-Q4_1	4.7
GGUF	i1-Q5K_S	5.1
GGUF	i1-Q5K_M	5.2
GGUF	i1-Q6K	6.0	practically like static Q6K

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.