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

Orion 14B LongChat 6.0bpw Exl by KnutJaegersberg

 »  All LLMs  »  KnutJaegersberg  »  Orion 14B LongChat 6.0bpw Exl   URL Share it on

  1   

Orion 14B LongChat 6.0bpw Exl is an open-source language model by KnutJaegersberg. Features: 14b LLM, VRAM: 11.5GB, Context: 195K, License: other, LLM Explorer Score: 0.12.

  Custom code   Orion   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/KnutJaegersberg/Orion-14B-LongChat-6.0bpw-exl 

Orion 14B LongChat 6.0bpw Exl Benchmarks

LLME Score: 0.11604
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Orion 14B LongChat 6.0bpw Exl (KnutJaegersberg/Orion-14B-LongChat-6.0bpw-exl)
🌟 Advertise your project 🚀

Orion 14B LongChat 6.0bpw Exl Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Multilingual text generation, Chat applications
Primary Use Cases:
Interactive chat, Multilingual understanding
Limitations:
Not suitable for tasks requiring legal compliance or national security without proper review
Considerations:
Ensure safe and compliant use
Additional Notes 
The Orion-14B-LongChat model excels in handling extremely long contexts, with robust multilingual understanding and state-of-the-art performance in token length handling.
Supported Languages 
English (Full), Japanese (High), Korean (High), Chinese (High)
Training Details 
Data Sources:
Diverse dataset of 2.5 trillion tokens
Data Volume:
2.5 trillion tokens
Methodology:
Pretrained on a diverse dataset, fine-tuned for specific tasks
Context Length:
320000
Model Architecture:
Large Language Model optimized for long-context text generation
Responsible Ai Considerations 
Accountability:
OrionStarAI
Mitigation Strategies:
Compliance efforts during data preparation
Input Output 
Input Format:
Text input
Accepted Modalities:
text
Output Format:
Text generation
Release Notes 
Version:
3.0
Date:
2023-10-05
Notes:
Optimized for long-text processing, supporting up to 320K tokens
Version:
2.0
Date:
2023-07-15
Notes:
Improved multilingual performance; added quantized versions
Version:
1.0
Date:
2023-04-01
Notes:
Initial release of the Orion-14B series, focusing on multilingual capabilities
LLM NameOrion 14B LongChat 6.0bpw Exl
Repository 🤗https://huggingface.co/KnutJaegersberg/Orion-14B-LongChat-6.0bpw-exl 
Model Size14b
Required VRAM11.5 GB
Updated2026-03-06
MaintainerKnutJaegersberg
Model Typeorion
Model Files  8.6 GB: 1-of-2   2.9 GB: 2-of-2
Model ArchitectureOrionForCausalLM
Licenseother
Context Length200000
Model Max Length200000
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 LongChat 6.0bpw Exl

Best Alternatives
Context / RAM
Downloads
Likes
Orion 14B LongChat195K / 29 GB725
Orion 14B Base Special4K / 29 GB751
Kor Resume Orion 14B4K / 29 GB290
Orion 14B Base4K / 29 GB40681
Orion 14B Chat RAG4K / 29 GB7832
Orion 14B Chat Int44K / 8.8 GB2328
Orion 14B Chat RAG Safetensors4K / 29 GB50
Orion 14B Chat Safetensors4K / 29 GB51
Orion 14B Base Int44K / 8.8 GB118
Orion 14B Chat Plugin4K / 29 GB238
Note: green Score (e.g. "73.2") means that the model is better than KnutJaegersberg/Orion-14B-LongChat-6.0bpw-exl.

Rank the Orion 14B LongChat 6.0bpw Exl 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? 52473 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer