LLM EXPLORER 59,358 MODELS INDEXED

Orion MoE8x7B by OrionStarAI

By OrionStarAI · 324 downloads
HF Repo ↗ Copy URL

Orion MoE8x7B is an open-source language model by OrionStarAI. Features: LLM, VRAM: 96.2GB, Context: 8K, LLM Explorer Score: 0.15.

  Arxiv:2409.01790   Code   Custom code   En   Ja   Ko   Model   Orion moe   Pytorch   Region:us   Sharded   Zh
Model Card on HF 🤗: https://huggingface.co/OrionStarAI/Orion-MoE8x7B 

Orion MoE8x7B Parameters and Internals

LLM NameOrion MoE8x7B
Repository 🤗https://huggingface.co/OrionStarAI/Orion-MoE8x7B 
Required VRAM96.2 GB
Updated2026-06-19
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