LLM EXPLORER 59,420 MODELS INDEXED

Llama 3 Korean Bllossom 70B by Bllossom

By Bllossom · 32 downloads
HF Repo ↗ Copy URL

Llama 3 Korean Bllossom 70B is an open-source language model by Bllossom. Features: 70b LLM, VRAM: 141.9GB, Context: 8K, License: llama3, LLM Explorer Score: 0.13.

  Arxiv:2403.10882   Arxiv:2403.11399 Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Conversational   En   Endpoints compatible   Ko   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Bllossom/llama-3-Korean-Bllossom-70B 

Llama 3 Korean Bllossom 70B Parameters and Internals

Model Type 
text generation, bilingual, vision-language
Use Cases 
Areas:
bilingual language processing, Korean language enhancement, research, commercial applications
Applications:
bilingual AI assistants, cultural translation, vision-language applications
Primary Use Cases:
Korean-English bilingual tasks, vocabulary expansion for Korean
Supported Languages 
en (fluent), ko (native)
Training Details 
Data Sources:
Korean-English parallel corpus, custom made instruction following data
Data Volume:
250GB
Methodology:
full fine-tuning with Korean data
Model Architecture:
LLama3 enhanced with knowledge linking, vocabulary expansion, instruction tuning, and human feedback
Input Output 
Accepted Modalities:
text, vision
Release Notes 
Version:
2.0
Date:
2024-04-25
Notes:
Based on LLama-3 with increased pre-training data.
Version:
1.0
Date:
2023-08-01
Notes:
Initial release based on LLama-2 with bilingual capabilities.
LLM NameLlama 3 Korean Bllossom 70B
Repository 🤗https://huggingface.co/Bllossom/llama-3-Korean-Bllossom-70B 
Base Model(s)  Meta Llama 3 70B   meta-llama/Meta-Llama-3-70B
Model Size70b
Required VRAM141.9 GB
Updated2026-08-24
MaintainerBllossom
Model Typellama
Model Files  4.6 GB: 1-of-30   4.7 GB: 2-of-30   5.0 GB: 3-of-30   5.0 GB: 4-of-30   4.7 GB: 5-of-30   4.7 GB: 6-of-30   4.7 GB: 7-of-30   5.0 GB: 8-of-30   5.0 GB: 9-of-30   4.7 GB: 10-of-30   4.7 GB: 11-of-30   4.7 GB: 12-of-30   5.0 GB: 13-of-30   5.0 GB: 14-of-30   4.7 GB: 15-of-30   4.7 GB: 16-of-30   4.7 GB: 17-of-30   5.0 GB: 18-of-30   5.0 GB: 19-of-30   4.7 GB: 20-of-30   4.7 GB: 21-of-30   4.7 GB: 22-of-30   5.0 GB: 23-of-30   5.0 GB: 24-of-30   4.7 GB: 25-of-30   4.7 GB: 26-of-30   4.7 GB: 27-of-30   5.0 GB: 28-of-30   5.0 GB: 29-of-30   2.1 GB: 30-of-30
Supported Languagesen ko
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.42.4
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 Korean Bllossom 70B

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB90695
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB76844
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB22122
Llama3 Function Calling 1048K1024K / 141.9 GB51
...a 3 70B Instruct Gradient 524K512K / 141.9 GB2423
...a 3 70B Instruct Gradient 262K256K / 141.9 GB2056
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB103
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB50
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB213
Yi 70B 200K RPMerge Franken195K / 142.4 GB101
Note: green Score (e.g. "73.2") means that the model is better than Bllossom/llama-3-Korean-Bllossom-70B.