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

MN 12B Starcannon V3 by nothingiisreal

 »  All LLMs  »  nothingiisreal  »  MN 12B Starcannon V3   URL Share it on

  289   
  Merged Model   Arxiv:2306.01708   Autotrain compatible Base model:anthracite-org/magn... Base model:nothingiisreal/mn-1...   Conversational   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nothingiisreal/MN-12B-Starcannon-v3 

MN 12B Starcannon V3 Benchmarks

MMLU Pro: 25.16
GPQA: 3.13
MUSR: 9.85
BBH: 30.87
IFEval: 38.07 vs 88 (so35)-56.7%
MATH Lvl 5: 6.87
LLME Score: 0.29226
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MN 12B Starcannon V3 (nothingiisreal/MN-12B-Starcannon-v3)

MN 12B Starcannon V3 Parameters and Internals

Model Type 
pre-trained language model, merge
Training Details 
Data Sources:
anthracite-org/magnum-12b-v2, nothingiisreal/MN-12B-Celeste-V1.9
Methodology:
TIES
LLM NameMN 12B Starcannon V3
Repository 🤗https://huggingface.co/nothingiisreal/MN-12B-Starcannon-v3 
Base Model(s)  Magnum 12B V2   nothingiisreal/MN-12B-Celeste-V1.9   anthracite-org/magnum-12b-v2   nothingiisreal/MN-12B-Celeste-V1.9
Merged ModelYes
Model Size12b
Required VRAM24.5 GB
Updated2024-12-26
Maintainernothingiisreal
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
Model ArchitectureMistralForCausalLM
Context Length1024000
Model Max Length1024000
Transformers Version4.43.4
Tokenizer ClassGPT2Tokenizer
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to MN 12B Starcannon V3

Best Alternatives
Context / RAM
Downloads
Likes
...s PersonalityEngine V1.1.0 12B1000K / 24.5 GB11312
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB2060397
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB10583622
VICIOUS MESH 12B BETA1000K / 24.5 GB802
MISCHIEVOUS 12B Mix 0.4v1000K / 24.5 GB1962
Dolphin 2.9.3 Mistral Nemo 12B1000K / 24.5 GB872291
VICIOUS MESH 12B ALPHA1000K / 24.5 GB591
MISCHIEVOUS 12B Mix III Ex V1000K / 24.5 GB2210
MISCHIEVOUS 12B1000K / 24.5 GB2362
VICIOUS MESH 12B GAMMA1000K / 24.5 GB361
Note: green Score (e.g. "73.2") means that the model is better than nothingiisreal/MN-12B-Starcannon-v3.

Rank the MN 12B Starcannon 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? 40248 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