LLM EXPLORER 67,808 MODELS INDEXED

Open Llama 2 Ko 7B by beomi

By beomi · 26 downloads

Open Llama 2 Ko 7B is an open-source language model by beomi. Features: 7b LLM, VRAM: 13.6GB, Context: 2K, License: mit, LLM Explorer Score: 0.1.

  En   Facebook   Ko   Kollama   Llama   Llama-2-ko   Llama2   Meta   Pytorch   Region:us   Safetensors   Sharded   Tensorflow

Open Llama 2 Ko 7B Parameters and Internals

Model Type 
text generation
Additional Notes 
The model is open for unrestricted use by everyone.
Supported Languages 
Korean (Enhanced proficiency)
Training Details 
Data Sources:
AI Hub, Modu Corpus, Korean Wikipedia
Data Volume:
Approximately 15 billion tokens
Methodology:
Optimized transformer architecture.
Context Length:
2000
Hardware Used:
TPU Research Cloud
Model Architecture:
Auto-regressive language model leveraging Llama-2 architecture
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Text
Release Notes 
Version:
2023.12.14
Date:
2023-12-14
Notes:
Initial Release of Open-Llama-2-Ko
LLM NameOpen Llama 2 Ko 7B
Repository πŸ€—https://huggingface.co/beomi/open-llama-2-ko-7b 
Model Size7b
Required VRAM13.6 GB
Updated2026-07-23
Maintainerbeomi
Model Typellama
Model Files  2.9 GB: 1-of-5   2.9 GB: 2-of-5   2.9 GB: 3-of-5   3.0 GB: 4-of-5   1.9 GB: 5-of-5   2.9 GB: 1-of-5   2.9 GB: 2-of-5   2.9 GB: 3-of-5   3.0 GB: 4-of-5   1.9 GB: 5-of-5
Supported Languagesko en
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.33.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size46336
Torch Data Typebfloat16

Best Alternatives to Open Llama 2 Ko 7B

Best Alternatives
Context / RAM
Downloads
Likes
1241024K / 16.1 GB930
1621024K / 16.1 GB600
1571024K / 16.1 GB1010
1181024K / 16.1 GB150
A5.41024K / 16.1 GB120
A3.41024K / 16.1 GB130
A2.41024K / 16.1 GB120
A6 L1024K / 16.1 GB2010
M1024K / 16.1 GB1270
2 Very Sci Fi1024K / 16.1 GB3170
Note: green Score (e.g. "73.2") means that the model is better than beomi/open-llama-2-ko-7b.