Kullm Polyglot 5.8B V2 by nlpai-lab

 ยป  All LLMs  ยป  nlpai-lab  ยป  Kullm Polyglot 5.8B V2   URL Share it on

  Autotrain compatible   Dataset:nlpai-lab/kullm-v2   Endpoints compatible   Gpt neox   Ko   Pytorch   Region:us   Sharded

Kullm Polyglot 5.8B V2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kullm Polyglot 5.8B V2 (nlpai-lab/kullm-polyglot-5.8b-v2)
๐ŸŒŸ Advertise your project ๐Ÿš€

Kullm Polyglot 5.8B V2 Parameters and Internals

Model Type 
parameter-efficient, fine-tuned
Additional Notes 
This model is a parameter-efficient variant of EleutherAI's polyglot-ko-5.8b, fine-tuned for Korean language tasks. Training was distributed across 4 GPUs with specific hyperparameter settings for optimization.
Supported Languages 
ko (Korean)
Training Details 
Data Sources:
nlpai-lab/kullm-v2
Methodology:
Fine-tuning with parameter-efficient methods
Hardware Used:
4x A100 80G GPUs
LLM NameKullm Polyglot 5.8B V2
Repository ๐Ÿค—https://huggingface.co/nlpai-lab/kullm-polyglot-5.8b-v2 
Model Size5.8b
Required VRAM23.6 GB
Updated2025-09-18
Maintainernlpai-lab
Model Typegpt_neox
Model Files  9.9 GB: 1-of-3   10.0 GB: 2-of-3   3.7 GB: 3-of-3
Supported Languagesko
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.29.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size30080
Torch Data Typefloat32

Best Alternatives to Kullm Polyglot 5.8B V2

Best Alternatives
Context / RAM
Downloads
Likes
Ai Script22K / 3.8 GB70
Ai Script2K / 3.8 GB70
KIT 5.8B2K / 23.4 GB23
KoAlpaca Polyglot 5.8B2K / 11.7 GB312666
KIT 5.8B2K / 23.5 GB8020
Polyglot Ko Empathy Chat 5.8B2K / 11.9 GB71
Model Resize Test2K / 23.4 GB210
KoQuality Polyglot 5.8B2K / 23.6 GB10443
ChatSKKU5.8B2K / 11.3 GB5360
Polyglot Ko 5.8B Inst All2K / 23.6 GB52
Note: green Score (e.g. "73.2") means that the model is better than nlpai-lab/kullm-polyglot-5.8b-v2.

Rank the Kullm Polyglot 5.8B V2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51435 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124