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

Orion 14B Base by OrionStarAI

 »  All LLMs  »  OrionStarAI  »  Orion 14B Base   URL Share it on

  1270   
  Autotrain compatible   Code   Custom code   En   Ja   Ko   Model   Orion   Pytorch   Region:us   Sharded   Zh
Model Card on HF 🤗: https://huggingface.co/OrionStarAI/Orion-14B-Base 

Orion 14B Base Benchmarks

ARC: 88.9 vs 96.7 (so35)-8.1%
HellaSwag: 78.5 vs 95.3 (gpt4)-17.6%
MMLU: 69.9 vs 88.3 (so35)-20.8%
GSM8K: 51.9 vs 96.4 (so35)-46.2%
OpenCompas: 62.6 vs 73.3 (gpt4)-14.6%
Exam: 73.5 vs 77.2 (gpt4)-4.8%
Language: 42.8 vs 62 (gpt4)-31%
Knowledge: 60 vs 73.5 (gpt4)-18.4%
Understand: 78.3 vs 70 (gpt4)11.9%
Reasoning: 60.3 vs 74.4 (gpt4)-19%
LLME Score: 0.15359
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Orion 14B Base (OrionStarAI/Orion-14B-Base)
🌟 Advertise your project 🚀

Orion 14B Base Parameters and Internals

Model Type 
text generation, chatbot
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
text generation, chatbot, language understanding
Considerations:
We strongly urge all users not to use the Orion-14B model for any activities that may harm national or social security or violate the law.
Additional Notes 
The Orion-14B series of models includes several variants, each optimized for different tasks and capable of handling extended context lengths with the long-chat versions, and quantized models for improved performance efficiency and reduced size.
Supported Languages 
en (high), zh (high), ja (high), ko (high)
Training Details 
Data Sources:
2.5T multilingual corpus including Chinese, English, Japanese, Korean
Data Volume:
2.5 trillion tokens
LLM NameOrion 14B Base
Repository 🤗https://huggingface.co/OrionStarAI/Orion-14B-Base 
Model Size14b
Required VRAM29 GB
Updated2025-09-23
MaintainerOrionStarAI
Model Typeorion
Model Files  15.7 GB: 1-of-2   13.3 GB: 2-of-2
Supported Languagesen zh ja ko
Model ArchitectureOrionForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.34.0
Tokenizer ClassOrionTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size84608
Torch Data Typebfloat16

Best Alternatives to Orion 14B Base

Best Alternatives
Context / RAM
Downloads
Likes
Orion 14B LongChat195K / 29 GB2725
Orion 14B LongChat 6.0bpw Exl195K / 11.5 GB52
Orion 14B Base Special4K / 29 GB201
Kor Resume Orion 14B4K / 29 GB290
Orion 14B Chat RAG4K / 29 GB7832
Orion 14B Chat Int44K / 8.8 GB2328
Orion 14B Chat RAG Safetensors4K / 29 GB60
Orion 14B Chat Safetensors4K / 29 GB61
Orion 14B Base Int44K / 8.8 GB218
Orion 14B Chat Plugin4K / 29 GB238

Rank the Orion 14B Base 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? 51534 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 v20241124
  Support LLM Explorer