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

KtdsbaseLM V0.13 Onbased Llama3.1 by AIDX-ktds

 »  All LLMs  »  AIDX-ktds  »  KtdsbaseLM V0.13 Onbased Llama3.1   URL Share it on

  12   

KtdsbaseLM V0.13 Onbased Llama3.1 is an open-source language model by AIDX-ktds. Features: 8b LLM, VRAM: 16.1GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.16.

Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Conversational Dataset:aidx-ktds/ko leaderboa...   Instruct   Ko   Ktds   Leaderboard   Llama   Llama3.1   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/AIDX-ktds/ktdsbaseLM-v0.13-onbased-llama3.1 

KtdsbaseLM V0.13 Onbased Llama3.1 Benchmarks

LLME Score: 0.15908
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
KtdsbaseLM V0.13 Onbased Llama3.1 (AIDX-ktds/ktdsbaseLM-v0.13-onbased-llama3.1)
🌟 Advertise your project 🚀

KtdsbaseLM V0.13 Onbased Llama3.1 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
education, business, research, culture, customer service
Applications:
Q&A systems, document summarization, sentiment analysis, translation services
Limitations:
Limited data on certain areas like international current events may affect accuracy, Limited logical reasoning capabilities, Potential for biased responses due to skewed data
Considerations:
Focus on Korean language and culture-specific applications
Additional Notes 
Model designed to reflect Korean societal values and cultural contexts.
Supported Languages 
ko (Proficient)
Training Details 
Data Sources:
Korean historical data, societal, financial, legal, tax, math, biology, physics, chemistry data
Data Volume:
3.6GB
Methodology:
Supervised Fine-Tuning (SFT)
Model Architecture:
Based on fine-tuned LlaMA3.0 8B for Korean cultural contexts
Input Output 
Input Format:
{"prompt": "prompt text", "completion": "ideal generated text"}
Accepted Modalities:
text
Output Format:
text
Release Notes 
Version:
v0.3
Date:
unknown
Notes:
Model fine-tuned with additional 200K data using SFT method
LLM NameKtdsbaseLM V0.13 Onbased Llama3.1
Repository 🤗https://huggingface.co/AIDX-ktds/ktdsbaseLM-v0.13-onbased-llama3.1 
Base Model(s)  meta-llama/Llama-3.1-8B-Instruct   meta-llama/Llama-3.1-8B-Instruct
Model Size8b
Required VRAM16.1 GB
Updated2026-03-07
MaintainerAIDX-ktds
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesko
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to KtdsbaseLM V0.13 Onbased Llama3.1

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB89119
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB93
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB4017
Cthulhu 8B V1.41048K / 16.1 GB139
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB344055
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
Zero Llama 3.1 8B Beta61048K / 16.1 GB51
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB53
Note: green Score (e.g. "73.2") means that the model is better than AIDX-ktds/ktdsbaseLM-v0.13-onbased-llama3.1.

Rank the KtdsbaseLM V0.13 Onbased Llama3.1 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? 52721 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