LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

DarkAtom 12B V3 by Khetterman

 »  All LLMs  »  Khetterman  »  DarkAtom 12B V3   URL Share it on

  166   
  Merged Model   12b   Autotrain compatible Base model:bacon666/phenom-12b... Base model:benhaotang/nemo-mat... Base model:fallenmerick/mn-chu... Base model:galrionsoftworks/ca... Base model:galrionsoftworks/pl... Base model:infermatic/mn-12b-i... Base model:luni/stardust-12b-v...   Base model:nohobby/insanityb Base model:nohobby/mn-12b-sisk... Base model:prodeusunity/stella... Base model:pyroserenus/orthrus... Base model:rityak/mn-maghin-12... Base model:rityak/mn-rocinante... Base model:royallab/mn-looseca... Base model:spow12/chatwaifu 12... Base model:thijsl202/madmix-un... Base model:trappu/abomination-... Base model:vongolachouko/starc...   Bfloat16   Chat   Conversational   Creative   Creative-writing   En   Endpoints compatible   Mistral   Not-for-all-audiences   Region:us   Roleplay   Ru   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Khetterman/DarkAtom-12B-v3 

DarkAtom 12B V3 Benchmarks

MMLU Pro: 28.29
GPQA: 6.38
MUSR: 16.12
BBH: 31.66
IFEval: 61.73 vs 88 (so35)-29.9%
MATH Lvl 5: 9.89
LLME Score: 0.35372
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DarkAtom 12B V3 (Khetterman/DarkAtom-12B-v3)

DarkAtom 12B V3 Parameters and Internals

LLM NameDarkAtom 12B V3
Repository 🤗https://huggingface.co/Khetterman/DarkAtom-12B-v3 
Base Model(s)  Bacon666/Phenom-12B-0.1   ...mo Math Science Philosophy 12B   MN Chunky Lotus 12B   Canidori 12B V1   Pleiades 12B V1   StarDust 12B V2   InsanityB   Nohobby/MN-12B-Siskin-v0.2   ProdeusUnity/Stellar-Odyssey-12b-v0.0   Pyroserenus/Orthrus-12b-v0.8   MN Maghin 12B   MN RocinanteCelestar 12B   MN LooseCannon 12B V2   spow12/ChatWaifu_12B_v2.0   Svak/MN-12B-Inferor-v0.0   MadMix Unleashed 12B   Abomination Merge Attempt 12B   VongolaChouko/Starcannon-Unleashed-12B-v1.0   Bacon666/Phenom-12B-0.1   benhaotang/nemo-math-science-philosophy-12B   FallenMerick/MN-Chunky-Lotus-12B   GalrionSoftworks/Canidori-12B-v1   GalrionSoftworks/Pleiades-12B-v1   Luni/StarDust-12b-v2   Nohobby/InsanityB   Nohobby/MN-12B-Siskin-v0.2   ProdeusUnity/Stellar-Odyssey-12b-v0.0   Pyroserenus/Orthrus-12b-v0.8   rityak/MN-Maghin-12B   rityak/MN-RocinanteCelestar-12B   royallab/MN-LooseCannon-12B-v2   spow12/ChatWaifu_12B_v2.0   Svak/MN-12B-Inferor-v0.0   ThijsL202/MadMix-Unleashed-12B   Trappu/Abomination-merge-attempt-12B   VongolaChouko/Starcannon-Unleashed-12B-v1.0
Merged ModelYes
Model Size12b
Required VRAM24.5 GB
Updated2024-12-22
MaintainerKhetterman
Model Typemistral
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesen ru
Model ArchitectureMistralForCausalLM
Context Length1024000
Model Max Length1024000
Transformers Version4.45.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to DarkAtom 12B V3

Best Alternatives
Context / RAM
Downloads
Likes
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB2072096
...s PersonalityEngine V1.1.0 12B1000K / 24.5 GB463
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB10680822
MISCHIEVOUS 12B Mix 0.4v1000K / 24.5 GB1861
VICIOUS MESH 12B BETA1000K / 24.5 GB251
Dolphin 2.9.3 Mistral Nemo 12B1000K / 24.5 GB912687
MISCHIEVOUS 12B1000K / 24.5 GB2272
MISCHIEVOUS 12B Mix III Ex V1000K / 24.5 GB1740
VICIOUS MESH 12B ALPHA1000K / 24.5 GB420
MISCHIEVOUS 12B Mix 0.2v1000K / 24.5 GB1451
Note: green Score (e.g. "73.2") means that the model is better than Khetterman/DarkAtom-12B-v3.

Rank the DarkAtom 12B V3 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 40066 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217
  Support LLM Explorer