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

KoAlpaca Polyglot 5.8B by beomi

 »  All LLMs  »  beomi  »  KoAlpaca Polyglot 5.8B   URL Share it on

  5902   
  Autotrain compatible Base model:eleutherai/polyglot... Base model:finetune:eleutherai...   Dataset:koalpaca-v1.1b   Endpoints compatible   Generated from trainer   Gpt-neox   Gpt neox   Ko   Koalpaca   Polyglot-ko   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/beomi/KoAlpaca-Polyglot-5.8B 

KoAlpaca Polyglot 5.8B Benchmarks

ARC: 27.65 vs 96.7 (so35)-71.4%
HellaSwag: 35.58 vs 95.3 (gpt4)-62.7%
MMLU: 24.72 vs 88.3 (so35)-72%
TruthfulQA: 39.74 vs 59 (gpt4)-32.6%
WinoGrande: 49.01 vs 87.5 (gpt4)-44%
GSM8K: 0.08 vs 96.4 (so35)-99.9%
LLME Score: 0.16908
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
KoAlpaca Polyglot 5.8B (beomi/KoAlpaca-Polyglot-5.8B)

KoAlpaca Polyglot 5.8B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, application development
Primary Use Cases:
text generation in Korean
Supported Languages 
Korean (fluent)
Training Details 
Data Sources:
KoAlpaca Dataset v1.1b
Methodology:
fine-tuning
Model Architecture:
GPT-NeoX
Release Notes 
Version:
v1.1b
Date:
2023.06.01
Notes:
Added Safetensor sharded model weight (max shard = 1GB)
LLM NameKoAlpaca Polyglot 5.8B
Repository 🤗https://huggingface.co/beomi/KoAlpaca-Polyglot-5.8B 
Base Model(s)  EleutherAI/polyglot-ko-5.8b   EleutherAI/polyglot-ko-5.8b
Model Size5.8b
Required VRAM11.7 GB
Updated2025-02-22
Maintainerbeomi
Model Typegpt_neox
Model Files  0.9 GB: 1-of-13   1.0 GB: 2-of-13   0.9 GB: 3-of-13   0.9 GB: 4-of-13   1.0 GB: 5-of-13   0.9 GB: 6-of-13   0.9 GB: 7-of-13   1.0 GB: 8-of-13   0.9 GB: 9-of-13   0.9 GB: 10-of-13   1.0 GB: 11-of-13   0.9 GB: 12-of-13   0.5 GB: 13-of-13   10.0 GB: 1-of-2   1.9 GB: 2-of-2   0.0 GB
Supported Languagesko
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.29.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size30080
Torch Data Typefloat16

Best Alternatives to KoAlpaca Polyglot 5.8B

Best Alternatives
Context / RAM
Downloads
Likes
Ai Script22K / 3.8 GB750
Ai Script2K / 3.8 GB750
KIT 5.8B2K / 23.4 GB73
KIT 5.8B2K / 23.5 GB20080
Polyglot Ko 5.8B Inst2K / 23.6 GB20170
ChatSKKU5.8B2K / 11.3 GB20470
KoQuality Polyglot 5.8B2K / 23.6 GB20273
Polyglot Ko Empathy Chat 5.8B2K / 11.9 GB171
Model Resize Test2K / 23.4 GB210
...olyglot 5.8B V2 Koalpaca V1.1B2K / 23.6 GB20240
Note: green Score (e.g. "73.2") means that the model is better than beomi/KoAlpaca-Polyglot-5.8B.

Rank the KoAlpaca Polyglot 5.8B 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? 43470 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 v20241227
  Support LLM Explorer