Orion MoE8x7B by OrionStarAI

 ยป  All LLMs  ยป  OrionStarAI  ยป  Orion MoE8x7B   URL Share it on

Orion MoE8x7B is an open-source language model by OrionStarAI. Features: LLM, VRAM: 96.2GB, Context: 8K, LLM Explorer Score: 0.16.

  Arxiv:2409.01790   Code   Custom code   En   Ja   Ko   Model   Orion moe   Pytorch   Region:us   Sharded   Zh

Orion MoE8x7B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Orion MoE8x7B (OrionStarAI/Orion-MoE8x7B)
๐ŸŒŸ Advertise your project ๐Ÿš€

Orion MoE8x7B Parameters and Internals

LLM NameOrion MoE8x7B
Repository ๐Ÿค—https://huggingface.co/OrionStarAI/Orion-MoE8x7B 
Required VRAM96.2 GB
Updated2026-04-10
MaintainerOrionStarAI
Model Typeorion_moe
Model Files  10.0 GB: 1-of-10   9.9 GB: 2-of-10   9.9 GB: 3-of-10   9.9 GB: 4-of-10   9.9 GB: 5-of-10   9.9 GB: 6-of-10   9.9 GB: 7-of-10   9.9 GB: 8-of-10   9.9 GB: 9-of-10   7.0 GB: 10-of-10
Supported Languagesen zh ja ko
Model ArchitectureOrionMOECausalLM
Context Length8192
Model Max Length8192
Transformers Version4.37.1
Tokenizer ClassOrionTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size113664
Torch Data Typebfloat16

Rank the Orion MoE8x7B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 52721 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a