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

Llama 3.2 Korean Bllossom 3B by Bllossom

 »  All LLMs  »  Bllossom  »  Llama 3.2 Korean Bllossom 3B   URL Share it on

  37601   
  Arxiv:2403.10882   Arxiv:2403.11399   Autotrain compatible   Conversational   En   Endpoints compatible   Ko   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Bllossom/llama-3.2-Korean-Bllossom-3B 

Llama 3.2 Korean Bllossom 3B Benchmarks

LLME Score: 0.32849
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3.2 Korean Bllossom 3B (Bllossom/llama-3.2-Korean-Bllossom-3B)

Llama 3.2 Korean Bllossom 3B Parameters and Internals

Model Type 
text generation, bilingual model
Additional Notes 
Model is designed with full-tuning using a vast amount of Korean data, maintaining English performance.
Supported Languages 
en (full), ko (full)
Training Details 
Data Volume:
150GB of refined Korean data
Methodology:
Instruction tuning
Hardware Used:
GPUs
Release Notes 
Version:
3B
Date:
2024-10-08
Notes:
Initial release of Bllossom-3B model with optimized Korean and English bilingual capabilities.
LLM NameLlama 3.2 Korean Bllossom 3B
Repository 🤗https://huggingface.co/Bllossom/llama-3.2-Korean-Bllossom-3B 
Base Model(s)  meta-llama/Meta-Llama-3.2-3B   meta-llama/Meta-Llama-3.2-3B
Model Size3b
Required VRAM6.5 GB
Updated2025-02-18
MaintainerBllossom
Model Typellama
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagesen ko
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.45.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3.2 Korean Bllossom 3B

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB14683981038
Llama 3.2 3B128K / 6.5 GB292320505
Hermes 3 Llama 3.2 3B128K / 6.5 GB20212142
... 3.2 3B Math Instruct RE1 ORPO128K / 6.5 GB1350
Calme 3.1 Llamaloi 3B128K / 10.6 GB29121
Dolphin3.0 Llama3.2 3B128K / 6.5 GB1641036
ReasoningCore 3B T1 1128K / 6.5 GB660
Llama 3.2 3B Instruct128K / 6.4 GB38327348
Llama 3.2 3B RP DeepThink128K / 7.2 GB2832
Orca Mini V9 5 3B Instruct128K / 6.5 GB1316
Note: green Score (e.g. "73.2") means that the model is better than Bllossom/llama-3.2-Korean-Bllossom-3B.

Rank the Llama 3.2 Korean Bllossom 3B 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? 43267 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