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

Custom KoLLM 13B V7 by PracticeLLM

 »  All LLMs  »  PracticeLLM  »  Custom KoLLM 13B V7   URL Share it on

  1001   
  Autotrain compatible Dataset:kyujinpy/kor-openorca-...   Endpoints compatible   Ko   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/PracticeLLM/Custom-KoLLM-13B-v7 

Custom KoLLM 13B V7 Benchmarks

LLME Score: 0.13774
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Custom KoLLM 13B V7 (PracticeLLM/Custom-KoLLM-13B-v7)
🌟 Advertise your project 🚀

Custom KoLLM 13B V7 Parameters and Internals

Model Type 
auto-regressive, language model
Supported Languages 
Korean (Proficient)
Training Details 
Data Sources:
kyujinpy/KOR-OpenOrca-Platypus-v3
Model Architecture:
LLaMA2 transformer architecture
LLM NameCustom KoLLM 13B V7
Repository 🤗https://huggingface.co/PracticeLLM/Custom-KoLLM-13B-v7 
Model Size13b
Required VRAM26.4 GB
Updated2025-08-23
MaintainerPracticeLLM
Model Typellama
Model Files  10.0 GB: 1-of-3   9.9 GB: 2-of-3   6.5 GB: 3-of-3   10.0 GB: 1-of-3   9.9 GB: 2-of-3   6.5 GB: 3-of-3
Supported Languagesko
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size46336
Torch Data Typefloat16

Best Alternatives to Custom KoLLM 13B V7

Best Alternatives
Context / RAM
Downloads
Likes
Luminaura RP 13B128K / 26 GB60
Yarn Llama 2 13B 128K128K / 26 GB201112
Agent Llama2 13B 80K80K / 26.4 GB50
Chat Llama2 13B 80K80K / 52.8 GB70
LongAlign 13B 64K64K / 26 GB3713
LongAlign 13B 64K64K / 26 GB1113
LongAlign 13B 64K Base64K / 26 GB343
LongAlign 13B 64K Base64K / 26 GB63
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB44
Openbuddy Llama2 13b64k V1564K / 26.1 GB72
Note: green Score (e.g. "73.2") means that the model is better than PracticeLLM/Custom-KoLLM-13B-v7.

Rank the Custom KoLLM 13B V7 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? 50836 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