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

SuperNova Medius by arcee-ai

 »  All LLMs  »  arcee-ai  »  SuperNova Medius   URL Share it on

  2786   
  Autotrain compatible Base model:finetune:qwen/qwen2...   Base model:qwen/qwen2.5-14b   Conversational   Endpoints compatible   Merge   Mergekit   Model-index   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/arcee-ai/SuperNova-Medius 

SuperNova Medius Benchmarks

MMLU Pro: 44.83
GPQA: 11.07
MUSR: 12.28
BBH: 48.01
IFEval: 71.84 vs 88 (so35)-18.4%
MATH Lvl 5: 15.33
LLME Score: 0.40156
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SuperNova Medius (arcee-ai/SuperNova-Medius)

SuperNova Medius Parameters and Internals

Model Type 
Language Model
Use Cases 
Areas:
Customer Support, Content Creation, Technical Assistance
Primary Use Cases:
complex customer interactions, creating high-quality, coherent content, programming and technical documentation
Additional Notes 
SuperNova-Medius achieves results that rival larger models while maintaining a compact size ideal for practical deployment.
Training Details 
Methodology:
Multi-architecture offline logit distillation with cross-architecture vocabulary alignment
Model Architecture:
Qwen2.5-14B-Instruct
LLM NameSuperNova Medius
Repository 🤗https://huggingface.co/arcee-ai/SuperNova-Medius 
Base Model(s)  Qwen/Qwen2.5-14B   Qwen/Qwen2.5-14B
Model Size14b
Required VRAM29.7 GB
Updated2025-02-05
Maintainerarcee-ai
Model Typeqwen2
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.8 GB: 6-of-6
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.46.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to SuperNova Medius

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB10662218
Qwen2.5 14B DeepSeek R1 1M986K / 29.7 GB5417
Impish QWEN 14B 1M986K / 29.7 GB9210
Calcium Opus 14B Elite 1M986K / 29.7 GB4610
Q2.5 14B Instruct 1M Harmony986K / 29.7 GB101
...wen2.5 14B Instruct 1M Unalign986K / 29.7 GB2890
Mergekit Model Stock Injkqri986K / 29.7 GB141
DeepSeek R1 Distill Qwen 14B128K / 29.6 GB173836311
Virtuoso Small V2128K / 29.7 GB46021
Virtuoso Small128K / 29.6 GB710765
Note: green Score (e.g. "73.2") means that the model is better than arcee-ai/SuperNova-Medius.

Rank the SuperNova Medius 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? 42565 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 v20241227
  Support LLM Explorer