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

Yi Ko DUS 9B by beomi

 »  All LLMs  »  beomi  »  Yi Ko DUS 9B   URL Share it on

  32   
  01-ai   Autotrain compatible   Doi:10.57967/hf/1707   En   Ko   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Yi   Yi-ko
Model Card on HF 🤗: https://huggingface.co/beomi/Yi-Ko-DUS-9B 

Yi Ko DUS 9B Benchmarks

LLME Score: 0.14449
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yi Ko DUS 9B (beomi/Yi-Ko-DUS-9B)
🌟 Advertise your project 🚀

Yi Ko DUS 9B Parameters and Internals

Model Type 
text-generation
Additional Notes 
BPE vocabulary expanded to better handle Korean text.
Supported Languages 
en (English), ko (Korean)
Training Details 
Data Sources:
A mix of Korean + English online data
Data Volume:
>120B tokens
Methodology:
DUS method applied
Context Length:
4000
Hardware Used:
TPU Research Cloud
Model Architecture:
Optimized transformer architecture based on Llama-2, can be loaded via LlamaForCausalLM
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text
Release Notes 
Version:
2024.01.29
Date:
2024-01-29
Notes:
Released Yi-Ko(KoEN)-DUS-9B model.
LLM NameYi Ko DUS 9B
Repository 🤗https://huggingface.co/beomi/Yi-Ko-DUS-9B 
Model Size9b
Required VRAM17.9 GB
Updated2025-07-07
Maintainerbeomi
Model Typellama
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   3.0 GB: 4-of-4
Supported Languagesen ko
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size78464
Torch Data Typebfloat16

Best Alternatives to Yi Ko DUS 9B

Best Alternatives
Context / RAM
Downloads
Likes
Xgen Small 9B Instruct R256K / 42.5 GB28375
Yi 9B 200K256K / 17.7 GB1241075
SekhmetX 9B V0.1 Test256K / 21.2 GB712
SekmetX 9B V0.1 Test256K / 21.2 GB692
Mike Hawk 9B256K / 21.3 GB413
Xgen Small 9B Base R256K / 42.5 GB3162
Austral Xgen 9B Winton256K / 21.3 GB102
...rce Xgen Small 9B Rebased V0.1256K / 42.5 GB170
...rce Xgen Small 9B Rebased V0.1256K / 42.5 GB140
BigYi 15.75B 200K256K / 30.3 GB90
Note: green Score (e.g. "73.2") means that the model is better than beomi/Yi-Ko-DUS-9B.

Rank the Yi Ko DUS 9B 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? 49452 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