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

Aria by rhymes-ai

 »  All LLMs  »  rhymes-ai  »  Aria   URL Share it on

  13627   
  Arxiv:2410.05993   Aria   Autotrain compatible Base model:finetune:rhymes-ai/... Base model:rhymes-ai/aria-base...   Conversational   Custom code   En   Image-text-to-text   Multimodal   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/rhymes-ai/Aria 

Aria Benchmarks

MMLU Pro: 37.83
GPQA: 14.99
MUSR: 14.05
BBH: 39.28
IFEval: 47.73 vs 88 (so35)-45.8%
MATH Lvl 5: 19.34
LLME Score: 0.41415
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Aria (rhymes-ai/Aria)

Aria Parameters and Internals

Model Type 
multimodal, aria
Use Cases 
Areas:
multimodal, language, coding
Additional Notes 
Aria is a lightweight and fast mixture-of-expert model with 3.9B activated parameters per token.
Supported Languages 
en (native)
Input Output 
Accepted Modalities:
text, image
LLM NameAria
Repository 🤗https://huggingface.co/rhymes-ai/Aria 
Base Model(s)  rhymes-ai/Aria-Base-64K   rhymes-ai/Aria-Base-64K
Model Size25.3b
Required VRAM50.6 GB
Updated2024-12-06
Maintainerrhymes-ai
Model Typearia
Model Files  4.9 GB: 1-of-12   4.6 GB: 2-of-12   4.1 GB: 3-of-12   4.6 GB: 4-of-12   4.1 GB: 5-of-12   4.6 GB: 6-of-12   4.1 GB: 7-of-12   4.6 GB: 8-of-12   4.1 GB: 9-of-12   4.6 GB: 10-of-12   4.1 GB: 11-of-12   2.2 GB: 12-of-12
Supported Languagesen
Model ArchitectureAriaForConditionalGeneration
Licenseapache-2.0
Transformers Version4.45.0
Tokenizer ClassLlamaTokenizer
Torch Data Typebfloat16

Rank the Aria 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? 46445 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