Model Details

Saltlux, AI Labs ์–ธ์–ด๋ชจ๋ธํŒ€์—์„œ ํ•™์Šต ๋ฐ ๊ณต๊ฐœํ•œ Ko-Llama3-Luxia-8B ๋ชจ๋ธ์€ Meta์—์„œ ์ถœ์‹œํ•œ Llama-3-8B ๋ชจ๋ธ์„ ํ•œ๊ตญ์–ด์— ํŠนํ™”ํ•œ ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค.

์ž์ฒด ๋ณด์œ ํ•˜๊ณ  ์žˆ๋Š” 1TB ์ด์ƒ์˜ ํ•œ๊ตญ์–ด ํ•™์Šต ๋ฐ์ดํ„ฐ ์ค‘, ์•ฝ 100GB ์ •๋„์˜ ๋ฐ์ดํ„ฐ๋ฅผ ์„ ๋ณ„ํ•˜์—ฌ ์‚ฌ์ „ํ•™์Šต์— ํ™œ์šฉํ•˜์˜€์Šต๋‹ˆ๋‹ค.

๋˜ํ•œ ๊ณต๊ฐœ๋œ Llama-3 Tokenizer๋ฅผ ํ•œ๊ตญ์–ด๋กœ ํ™•์žฅํ•˜๊ณ  ์‚ฌ์ „ํ•™์Šต์— ํ™œ์šฉํ–ˆ์Šต๋‹ˆ๋‹ค.

  • Meta Llama-3: Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
  • License: Llama3 License https://llama.meta.com/llama3/license

Intended Use

Ko-Llama3-Luxia-8B๋Š” ์—ฐ๊ตฌ์šฉ์œผ๋กœ ์ œ์ž‘๋˜์—ˆ์œผ๋ฉฐ, ๋‹ค์–‘ํ•œ ์ž์—ฐ์–ด ์ƒ์„ฑ ํƒœ์Šคํฌ๋ฅผ ์œ„ํ•ด ์ž์œ ๋กญ๊ฒŒ ํ•™์Šต ๋ฐ ํ™œ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

How to Use

ํ•ด๋‹น ๋ชจ๋ธ ์นด๋“œ์—๋Š” Ko-Llama3-Luxia-8B ๋ชจ๋ธ๊ณผ transformers ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ ๊ธฐ๋ฐ˜์˜ ์˜ˆ์‹œ ์ฝ”๋“œ๋ฅผ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.

import transformers
import torch

model_id = "saltlux/Ko-Llama3-Luxia-8B"

pipeline = transformers.pipeline(
    "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
)
pipeline("<|begin_of_text|>์•ˆ๋…•ํ•˜์„ธ์š”. ์†”ํŠธ๋ฃฉ์Šค AI Labs ์ž…๋‹ˆ๋‹ค.")

Training Details

ํ•œ๊ตญ์–ด ํŠนํ™”๋ฅผ ์œ„ํ•œ ์‚ฌ์ „ํ•™์Šต ๋ฐ์ดํ„ฐ๋Š” Saltlux์—์„œ ๋ณด์œ ํ•œ ๋‰ด์Šค, ๋ฒ•๋ฅ , ํŠนํ—ˆ, ์˜๋ฃŒ, ์—ญ์‚ฌ, ์‚ฌํšŒ, ๋ฌธํ™”, ๋Œ€ํ™”(๋ฌธ์–ด/๊ตฌ์–ด) ๋“ฑ์˜ ๋„๋ฉ”์ธ์œผ๋กœ ๊ตฌ์„ฑ๋œ 100GB ์ˆ˜์ค€์˜ ์ฝ”ํผ์Šค(~2023๋…„)๋ฅผ ํ™œ์šฉํ•˜์˜€์Šต๋‹ˆ๋‹ค.

  • ํ˜„์žฌ ์ œ๊ณต๋˜๋Š” ๋ชจ๋ธ์€ 1 Epoch ํ•™์Šต๋œ ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค.

Use Device

์‚ฌ์ „ํ•™์Šต์€ NVIDIA H100 80GB * 8EA ์žฅ๋น„๋ฅผ ํ™œ์šฉํ•˜์—ฌ ์ง„ํ–‰ํ•˜์˜€์Šต๋‹ˆ๋‹ค.

Training Hyperparameters

Model Params Context length GQA Learning rate Batch Precision
Ko-Llama3-Luxia-8B 8B 8k yes 1e-5 128 bf16

Tokenizer

Llama-3-Tokenizer๋ฅผ ํ•œ๊ตญ์–ด ํŠนํ™”ํ•˜๊ธฐ ์œ„ํ•ด ํ•œ๊ตญ์–ด ํ† ํฐ 17,536๊ฐœ๋ฅผ ์ถ”๊ฐ€ํ•˜๊ณ  ํ™œ์šฉํ•˜์˜€์Šต๋‹ˆ๋‹ค.

Model Vocab Size
Llama-3 128,256
Ko-Llama3-Luxia-8B 145,792

Tokenizer Result

  • Ko

    ์ž…๋ ฅ Llama-3 Ko-Llama3-Luxia-8B
    ์š”์ฆ˜ ๋‚ ์”จ๊ฐ€ ๋„ˆ๋ฌด ์˜ค๋ฝ๊ฐ€๋ฝํ•ด์„œ ์•„์ง๋„ ๊ฒจ์šธ์˜ท์„ ๋ชป์น˜์› ์–ด์š”.. ['์š”', '์ฆ˜', ' ๋‚ ', '์”จ', '๊ฐ€', ' ๋„ˆ๋ฌด', ' ์˜ค', '๋ฝ', '๊ฐ€', '๋ฝ', 'ํ•ด์„œ', ' ์•„์ง', '๋„', ' ๊ฒจ', '์šธ', '๏ฟฝ', '๏ฟฝ', '์„', ' ๋ชป', '์น˜', '์› ', '์–ด์š”', '..'] ['์š”์ฆ˜', ' ๋‚ ์”จ', '๊ฐ€', ' ๋„ˆ๋ฌด', ' ์˜ค๋ฝ', '๊ฐ€๋ฝ', 'ํ•ด์„œ', ' ์•„์ง', '๋„', ' ๊ฒจ์šธ', '์˜ท', '์„', ' ๋ชป', '์น˜', '์› ', '์–ด์š”', '..']
    ๋ง›์žˆ๋Š” ๋ฐฅ์„ ๋“œ์…จ์Šต๋‹ˆ๊นŒ? ๋ง›์ด ๊ถ๊ธˆํ•˜๋„ค์š”. ['๋ง›', '์žˆ๋Š”', ' ๏ฟฝ', '๏ฟฝ', '์„', ' ๋“œ', '์…จ', '์Šต', '๋‹ˆ๊นŒ', '?', ' ๋ง›', '์ด', ' ๊ถ๊ธˆ', 'ํ•˜', '๋„ค์š”', '.'] ['๋ง›', '์žˆ๋Š”', ' ๋ฐฅ', '์„', ' ๋“œ์…จ', '์Šต', '๋‹ˆ๊นŒ', '?', ' ๋ง›', '์ด', ' ๊ถ๊ธˆ', 'ํ•˜', '๋„ค์š”', '.']
    ๋Œ€๋ฒ•์›๋ถ€ํ„ฐ ํ•˜๊ธ‰์‹ฌ ํŒ๋ก€๊นŒ์ง€ ์›ํ•˜๋Š” ํŒ๋ก€๋ฅผ ์ฐพ๋Š” ๊ฐ€์žฅ ๋น ๋ฅธ ๋ฐฉ๋ฒ• - ์„œ๋ฉด ๊ฒ€์ƒ‰, ์š”์ฒญ ํŒ๋ก€, ์œ ์‚ฌ ํŒ๋ก€, AI ์ถ”์ฒœ, ํŒ๋ก€ ๋ฐ ๋ฒ•๋ น ๊ฒ€์ƒ‰. ['๋Œ€', '๋ฒ•', '์›', '๋ถ€ํ„ฐ', ' ํ•˜', '๊ธ‰', '์‹ฌ', ' ํŒ', '๋ก€', '๊นŒ์ง€', ' ์›', 'ํ•˜๋Š”', ' ํŒ', '๋ก€', '๋ฅผ', ' ์ฐพ', '๋Š”', ' ๊ฐ€์žฅ', ' ๋น ', '๋ฅธ', ' ๋ฐฉ๋ฒ•', ' -', ' ์„œ', '๋ฉด', ' ๊ฒ€์ƒ‰', ',', ' ์š”์ฒญ', ' ํŒ', '๋ก€', ',', ' ์œ ', '์‚ฌ', ' ํŒ', '๋ก€', ',', ' AI', ' ์ถ”์ฒœ', ',', ' ํŒ', '๋ก€', ' ๋ฐ', ' ๋ฒ•', '๋ น', ' ๊ฒ€์ƒ‰', '.'] ['๋Œ€', '๋ฒ•', '์›', '๋ถ€ํ„ฐ', ' ํ•˜', '๊ธ‰', '์‹ฌ', ' ํŒ๋ก€', '๊นŒ์ง€', ' ์›', 'ํ•˜๋Š”', ' ํŒ๋ก€', '๋ฅผ', ' ์ฐพ', '๋Š”', ' ๊ฐ€์žฅ', ' ๋น ๋ฅธ', ' ๋ฐฉ๋ฒ•', ' -', ' ์„œ๋ฉด', ' ๊ฒ€์ƒ‰', ',', ' ์š”์ฒญ', ' ํŒ๋ก€', ',', ' ์œ ์‚ฌ', ' ํŒ๋ก€', ',', ' AI', ' ์ถ”์ฒœ', ',', ' ํŒ๋ก€', ' ๋ฐ', ' ๋ฒ•๋ น', ' ๊ฒ€์ƒ‰', '.']
    ๋ณธ ๋ฐœ๋ช…์€ ๊ธˆ์†ํŒ์˜ ๋‹ค์ˆ˜ ๋ถ€๋ถ„์„ ์—์นญ์‹œ์ผœ ํŠน์ • ๋ฌด๋Šฌ๋ชจ์–‘์„ ํ˜•์„ฑํ•˜๋Š” ๊ฑด์ถ•์šฉ ๊ธˆ์†์žฌ ์žฅ์‹ํŒ์œผ๋กœ ์ด๋ฃจ์–ด์ง„ ๊ฒƒ์— ํŠน์ง•์ด ์žˆ๋‹ค. ['๋ณธ', ' ๋ฐœ', '๋ช…', '์€', ' ๊ธˆ', '์†', 'ํŒ', '์˜', ' ๋‹ค', '์ˆ˜', ' ๋ถ€๋ถ„', '์„', ' ์—', '์นญ', '์‹œ', '์ผœ', ' ํŠน', '์ •', ' ๋ฌด', '๏ฟฝ', '๏ฟฝ', '๋ชจ', '์–‘', '์„', ' ํ˜•', '์„ฑ', 'ํ•˜๋Š”', ' ๊ฑด', '์ถ•', '์šฉ', ' ๊ธˆ', '์†', '์žฌ', ' ์žฅ', '์‹', 'ํŒ', '์œผ๋กœ', ' ์ด๋ฃจ', '์–ด์ง„', ' ๊ฒƒ', '์—', ' ํŠน', '์ง•', '์ด', ' ์žˆ๋‹ค', '.'] ['๋ณธ', ' ๋ฐœ๋ช…', '์€', ' ๊ธˆ์†', 'ํŒ', '์˜', ' ๋‹ค์ˆ˜', ' ๋ถ€๋ถ„', '์„', ' ์—์นญ', '์‹œ', '์ผœ', ' ํŠน์ •', ' ๋ฌด๋Šฌ', '๋ชจ', '์–‘', '์„', ' ํ˜•์„ฑ', 'ํ•˜๋Š”', ' ๊ฑด์ถ•', '์šฉ', ' ๊ธˆ์†', '์žฌ', ' ์žฅ์‹', 'ํŒ', '์œผ๋กœ', ' ์ด๋ฃจ์–ด์ง„', ' ๊ฒƒ', '์—', ' ํŠน์ง•', '์ด', ' ์žˆ๋‹ค', '.']
    ๊ณจ๋‹ค๊ณต์ฆ์€ ์™œ ์ƒ๊ธฐ๋Š”๊ฑฐ์—์š”? ๊ทธ๋ฆฌ๊ณ  ์น˜๋ฃŒํ•˜๋ ค๋ฉด ์–ด๋–ป๊ฒŒํ•ด์•ผํ•˜์ฃ ? ['๊ณจ', '๋‹ค', '๊ณต', '์ฆ', '์€', ' ์™œ', ' ์ƒ', '๊ธฐ๋Š”', '๊ฑฐ', '์—', '์š”', '?', ' ๊ทธ๋ฆฌ๊ณ ', ' ์น˜', '๋ฃŒ', 'ํ•˜๋ ค', '๋ฉด', ' ์–ด๋–ป๊ฒŒ', 'ํ•ด์•ผ', 'ํ•˜', '์ฃ ', '?'] ['๊ณจ', '๋‹ค', '๊ณต์ฆ', '์€', ' ์™œ', ' ์ƒ', '๊ธฐ๋Š”', '๊ฑฐ', '์—', '์š”', '?', ' ๊ทธ๋ฆฌ๊ณ ', ' ์น˜๋ฃŒ', 'ํ•˜๋ ค', '๋ฉด', ' ์–ด๋–ป๊ฒŒ', 'ํ•ด์•ผ', 'ํ•˜', '์ฃ ', '?']
  • En

    ์ž…๋ ฅ Llama-3 Ko-Llama3-Luxia-8B
    Korean cuisine, hanguk yori, or hansik, has evolved through centuries of social and political change. ['K', 'orean', ' cuisine', ',', ' h', 'angu', 'k', ' y', 'ori', ',', ' or', ' hans', 'ik', ',', ' has', ' evolved', ' through', ' centuries', ' of', ' social', ' and', ' political', ' change', '.'] ['K', 'orean', ' cuisine', ',', ' h', 'angu', 'k', ' y', 'ori', ',', ' or', ' hans', 'ik', ',', ' has', ' evolved', ' through', ' centuries', ' of', ' social', ' and', ' political', ' change', '.']
    Son Heung-min is a South Korean professional footballer who plays as a forward for and captains both Premier League club Tottenham Hotspur and the South Korea national team. ['Son', ' He', 'ung', '-min', ' is', ' a', ' South', ' Korean', ' professional', ' football', 'er', ' who', ' plays', ' as', ' a', ' forward', ' for', ' and', ' captains', ' both', ' Premier', ' League', ' club', ' Tottenham', ' Hot', 'sp', 'ur', ' and', ' the', ' South', ' Korea', ' national', ' team', '.'] ['Son', ' He', 'ung', '-min', ' is', ' a', ' South', ' Korean', ' professional', ' football', 'er', ' who', ' plays', ' as', ' a', ' forward', ' for', ' and', ' captains', ' both', ' Premier', ' League', ' club', ' Tottenham', ' Hot', 'sp', 'ur', ' and', ' the', ' South', ' Korea', ' national', ' team', '.']

Inference Result

Llama-3 Ko-Llama3-Luxia-8B
์บ๋ฆฌ๋น„์•ˆ๋ฒ ์ด๋Š” ์šฉ์ธ์— ์œ„์น˜ํ•œ ์บ๋ฆฌ๋น„์•ˆ ๋ฒ ์ด์˜ ๊ณต์‹ ์˜จ๋ผ์ธ ์นด์ง€๋…ธ์ž…๋‹ˆ๋‹ค. ์บ๋ฆฌ๋น„์•ˆ ๋ฒ ์ด๋Š” 1994๋…„๋ถ€ํ„ฐ ์šด์˜๋˜์–ด ์™”์œผ๋ฉฐ, 2005๋…„์— ์˜จ๋ผ์ธ์œผ๋กœ ์˜คํ”ˆํ–ˆ์Šต๋‹ˆ๋‹ค. ์ด ์‚ฌ์ดํŠธ๋Š” ์˜๊ตญ์—์„œ ์šด์˜๋˜๋Š” ๋ผ์ด์„ผ์Šค๋ฅผ ๊ฐ€์ง€๊ณ  ์žˆ์œผ๋ฉฐ, ์˜๊ตญ ์ •๋ถ€๊ฐ€ ์Šน์ธํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.\n์บ๋ฆฌ๋น„์•ˆ ๋ฒ ์ด๋Š” ๋‹ค์–‘ํ•œ ๊ฒŒ์ž„์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. ์Šฌ๋กฏ ๋จธ์‹ , ๋ธ”๋ž™์žญ, ๋ฃฐ๋ ›, ํฌ์ปค, ๋ฐ”์นด๋ผ ๋“ฑ์ด ์žˆ์Šต๋‹ˆ๋‹ค. ๋˜ํ•œ, ์บ๋ฆฌ๋น„์•ˆ ๋ฒ ์ด๋Š” ๋‹ค์–‘ํ•œ ๋ณด๋„ˆ์Šค์™€ ํ”„๋กœ๋ชจ์…˜์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. ์˜ˆ๋ฅผ ๋“ค์–ด, ์‹ ๊ทœ ํšŒ์›์—๊ฒŒ๋Š” ๊ฐ€์ž… ์‹œ 100% ๋ฐฐํŒ… ๋ณด๋„ˆ์Šค๊ฐ€ ์ฃผ์–ด์ง‘๋‹ˆ๋‹ค. ๋˜ํ•œ, ๋งค์ฃผ๋งˆ๋‹ค ๋‹ค์–‘ํ•œ ์ด๋ฒคํŠธ์™€ ํ”„๋กœ๋ชจ์…˜์ด ์ง„ํ–‰๋ฉ๋‹ˆ๋‹ค.<์ดํ•˜ ์ƒ๋žต> ์บ๋ฆฌ๋น„์•ˆ๋ฒ ์ด๋Š” ์šฉ์ธ์— ์žˆ๋Š” ๋†€์ด๊ณต์›์ธ๋ฐ์š”. ์บ๋ฆฌ๋น„์•ˆ๋ฒ ์ด์˜ ๊ฒฝ์šฐ์—๋Š” ์›Œํ„ฐํŒŒํฌ์™€ ๋†€์ด๊ณต์›์ด ๊ฐ™์ด ์žˆ์Šต๋‹ˆ๋‹ค. ๊ทธ๋ž˜์„œ ์—ฌ๋ฆ„์—๋Š” ๋ฌผ๋†€์ด๋ฅผ ์ฆ๊ธฐ๊ณ  ๊ฒจ์šธ์—๋Š” ๋ˆˆ์ฐ๋งค๋ฅผ ํƒˆ ์ˆ˜ ์žˆ์–ด์„œ ์‚ฌ๊ณ„์ ˆ ๋‚ด๋‚ด ์ฆ๊ธธ ์ˆ˜ ์žˆ๋Š” ๊ณณ์ด์ฃ .\n์บ๋ฆฌ๋น„์•ˆ๋ฒ ์ด๋ฅผ ์ด์šฉํ•˜๋ ค๋ฉด ์šฐ์„  ํ™ˆํŽ˜์ด์ง€์—์„œ ์ž…์žฅ๊ถŒ์„ ๊ตฌ๋งคํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค. ๊ทธ๋ฆฌ๊ณ  ์บ๋ฆฌ๋น„์•ˆ๋ฒ ์ด์˜ ๊ฒฝ์šฐ์—๋Š” 1๋…„ ๋™์•ˆ ์ž์œ ๋กญ๊ฒŒ ์ด์šฉํ•  ์ˆ˜ ์žˆ๋Š” ์—ฐ๊ฐ„ํšŒ์›๊ถŒ๋„ ํŒ๋งคํ•˜๋Š”๋ฐ์š”. ์—ฐ๊ฐ„ํšŒ์›๊ถŒ์€ ์„ฑ์ธ๊ณผ ์–ด๋ฆฐ์ด ๋ชจ๋‘ ๊ตฌ๋งค๊ฐ€ ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค.<์ดํ•˜ ์ƒ๋žต>
๋ฒ ํŠธ๋‚จ ์Œ€๊ตญ์ˆ˜๋Š” ํ•œ๊ตญ์˜ ๊ตญ๋ฐฅ๊ณผ ๋น„์Šทํ•œ ์Œ์‹์ž…๋‹ˆ๋‹ค. ๋ฒ ํŠธ๋‚จ ์Œ€๊ตญ์ˆ˜์—๋Š” ์Œ€, ๋ผ์ง€๊ณ ๊ธฐ, ๊ณ„๋ž€, ์–‘ํŒŒ, ๋งˆ๋Š˜, ์ƒ๊ฐ•, ๊ณ ์ถ” ๋“ฑ์ด ๋“ค์–ด๊ฐ‘๋‹ˆ๋‹ค.\n1. ์Œ€์„ ์”ป์–ด ๋ฌผ์— ๋‹ด๊ฐ€ ๋‘ก๋‹ˆ๋‹ค.\n2. ๋ผ์ง€๊ณ ๊ธฐ๋ฅผ ์ž˜๊ฒŒ ์ฐ๊ณ , ์–‘ํŒŒ์™€ ๋งˆ๋Š˜, ์ƒ๊ฐ•, ๊ณ ์ถ”๋ฅผ ๋‹ค์ ธ์ค๋‹ˆ๋‹ค.\n3. ํŒฌ์— ๊ธฐ๋ฆ„์„ ๋‘๋ฅด๊ณ  ๋ผ์ง€๊ณ ๊ธฐ๋ฅผ ๋ณถ๋‹ค๊ฐ€ ์–‘ํŒŒ์™€ ๋งˆ๋Š˜, ์ƒ๊ฐ•, ๊ณ ์ถ”๋ฅผ ๋„ฃ์Šต๋‹ˆ๋‹ค.\n4. ๊ณ„๋ž€์„ ํ’€์–ด์„œ ๋„ฃ๊ณ , ๊ฐ„์žฅ์„ ๋„ฃ์–ด ๋ณถ์•„์ค๋‹ˆ๋‹ค.\n5. ์Œ€์„ ๋ฌผ์— ๋ถˆ๋ ค์„œ ๋„ฃ๊ณ , ๋“์œผ๋ฉด ์†Œ๊ธˆ๊ณผ ํ›„์ถ”๋ฅผ ๋„ฃ์–ด์ค๋‹ˆ๋‹ค.\n6. ์Œ€๊ตญ์ˆ˜๋ฅผ ๋จน๊ธฐ ์ข‹์€ ์ƒํƒœ๊ฐ€ ๋˜๋ฉด ๊บผ๋‚ด ์ค๋‹ˆ๋‹ค.\n7. ์Œ€๊ตญ์ˆ˜์˜ ์œ„์— ๋ผ์ง€๊ณ ๊ธฐ์™€ ๊ณ„๋ž€์„ ์–น์–ด ๋จน์Šต๋‹ˆ๋‹ค.\nVietnamese rice noodles are similar to Korean rice porridge. Vietnamese rice noodles contain rice, pork, eggs, onions, garlic, ginger and chili peppers.<์ดํ•˜ ์ƒ๋žต> ๋ฒ ํŠธ๋‚จ ์Œ€๊ตญ์ˆ˜๋Š” ์ผ๋ฐ˜์ ์œผ๋กœ ์–‡๊ฒŒ ์ฌ ์Œ€๊ฐ€๋ฃจ๋กœ ๋งŒ๋“  ๋ฉด์„ ์‚ฌ์šฉํ•ฉ๋‹ˆ๋‹ค. ๋ฉด์€ ๋œจ๊ฑฐ์šด ๋ฌผ์— ์‚ถ์•„์„œ ์ฐฌ๋ฌผ์— ํ—น๊ตฌ์–ด๋ƒ…๋‹ˆ๋‹ค. ๋ฉด์ด ์‚ถ์•„์ง€๋ฉด ์œก์ˆ˜์™€ ์•ผ์ฑ„๋ฅผ ๋„ฃ๊ณ  ๋“์ž…๋‹ˆ๋‹ค. ์œก์ˆ˜๋ฅผ ๋งŒ๋“ค ๋•Œ๋Š” ๋‹ญ๊ณ ๊ธฐ, ์†Œ๊ณ ๊ธฐ, ๋ผ์ง€๊ณ ๊ธฐ ๋“ฑ ๋‹ค์–‘ํ•œ ์žฌ๋ฃŒ๋ฅผ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์•ผ์ฑ„๋กœ๋Š” ๋‹น๊ทผ, ์–‘ํŒŒ, ํŒŒ ๋“ฑ์„ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.<์ดํ•˜ ์ƒ๋žต>
ํ•œ๊ตญ์˜ ์ „ํ†ต์˜์ƒ์ธ ํ•œ๋ณต๊ณผ ์ผ๋ณธ์˜ ์ „ํ†ต์˜์ƒ์ธ ์š”๋กœ์นด๋ฏธ๋Š” ๋ชจ๋‘ 5๋Œ€๋ฅ™์˜ ๋ฌธํ™”๋ฅผ ์ˆ˜์šฉํ•˜๊ณ , ๊ฐ๊ธฐ ๋‹ค๋ฅธ ์ง€์—ญ์˜ ํŠน์ง•์„ ๋ฐ˜์˜ํ•œ ์˜์ƒ์„ ๊ฐ–์ถ”๊ณ  ์žˆ๋‹ค. ์ด๋Ÿฌํ•œ ์˜์ƒ์˜ ํŠน์ง•์€ ๊ฐ๊ฐ์˜ ๊ตญ๊ฐ€์—์„œ ๋ฐœ์ „ํ•ด ์˜จ ์—ญ์‚ฌ์™€ ๋ฌธํ™”์— ๊ธฐ์ดˆํ•œ๋‹ค. ํ•œํŽธ, ํ•œ๊ตญ์˜ ํ•œ๋ณต๊ณผ ์ผ๋ณธ์˜ ์š”๋กœ์นด๋ฏธ๋Š” ์„œ๋กœ ๋น„์Šทํ•œ ํ˜•ํƒœ๋ฅผ ๊ฐ€์ง€๊ณ  ์žˆ์ง€๋งŒ, ๊ทธ ์˜๋ฏธ๋Š” ๋‹ค๋ฅด๋‹ค. ํ•œ๋ณต์€ ํ•œ๊ตญ์ธ์˜ ์ •์ฒด์„ฑ์„ ๋‚˜ํƒ€๋‚ด๋ฉฐ, ์š”๋กœ์นด๋ฏธ๋Š” ์ผ๋ณธ์ธ์˜ ์ •์ฒด์„ฑ์„ ๋‚˜ํƒ€๋‚ธ๋‹ค. ๋”ฐ๋ผ์„œ ์ด ๋‘ ๊ฐ€์ง€ ์˜์ƒ์€ ์„œ๋กœ ๋‹ค๋ฅธ ๋ฌธํ™”์  ๋ฐฐ๊ฒฝ์„ ๊ฐ€์ง„ ์‚ฌ๋žŒ๋“ค์˜ ์ •์ฒด์„ฑ ํ‘œํ˜„์— ์‚ฌ์šฉ๋œ๋‹ค.\nThe traditional costumes of Korea and Japan are hanbok and yorokami respectively. Both have been influenced by the cultures of other countries and reflect the characteristics of their respective regions. The distinctive features of these costumes are based on the history and culture of each country. However, although hanbok and yorokami share similar forms, they have different meanings. Hanbok represents Korean identity while yorokami represents Japanese identity. <์ดํ•˜ ์ƒ๋žต> ํ•œ๊ตญ์˜ ์ „ํ†ต์˜์ƒ์ธ ํ•œ๋ณต์€ ํ•œ๊ตญ์˜ ๋ฌธํ™”๋ฅผ ๋Œ€ํ‘œํ•˜๋Š” ์ƒ์ง•๋ฌผ์ด๋‹ค. ํ•˜์ง€๋งŒ ์ตœ๊ทผ์—๋Š” ํ•œ๋ณต์„ ์ž…๋Š” ์‚ฌ๋žŒ๋“ค์ด ์ ์  ์ค„์–ด๋“ค๊ณ  ์žˆ๋‹ค. ์ด๋Š” ์—ฌ๋Ÿฌ ๊ฐ€์ง€ ์ด์œ ๊ฐ€ ์žˆ๊ฒ ์ง€๋งŒ, ๊ทธ ์ค‘ ํ•˜๋‚˜๋Š” ํ•œ๋ณต์ด ๋ถˆํŽธํ•˜๊ธฐ ๋•Œ๋ฌธ์ผ ๊ฒƒ์ด๋‹ค. ํ•œ๋ณต์€ ์ผ๋ฐ˜์ ์ธ ์˜ท๋ณด๋‹ค ๋” ๋งŽ์€ ๋ถ€๋ถ„์„ ๋ฎ์–ด์•ผ ํ•˜๊ณ , ์›€์ง์ด๊ธฐ ์–ด๋ ต๋‹ค. ๋˜ํ•œ, ํ•œ๋ณต์€ ์„ธํƒํ•˜๊ธฐ๊ฐ€ ์–ด๋ ต๊ณ , ๊ด€๋ฆฌํ•˜๊ธฐ๋„ ์‰ฝ์ง€ ์•Š๋‹ค.\nํ•˜์ง€๋งŒ ํ•œ๋ณต์€ ๋‹จ์ˆœํžˆ ๋ถˆํŽธํ•˜๊ณ  ๊ด€๋ฆฌํ•˜๊ธฐ ์–ด๋ ค์šด ์˜ท์ด ์•„๋‹ˆ๋‹ค. ํ•œ๋ณต์€ ํ•œ๊ตญ์ธ์˜ ์—ญ์‚ฌ์™€ ๋ฌธํ™”๋ฅผ ๋‹ด๊ณ  ์žˆ๋Š” ์†Œ์ค‘ํ•œ ๋ฌธํ™”์œ ์‚ฐ์ด๋‹ค. ํ•œ๋ณต์€ ํ•œ๊ตญ์˜ ์ „ํ†ต๊ณผ ๋ฏธ๋ฅผ ํ‘œํ˜„ํ•˜๋Š” ์ค‘์š”ํ•œ ์ˆ˜๋‹จ์ด๋ฉฐ, ํ•œ๊ตญ์˜ ์ •์ฒด์„ฑ์„ ๋‚˜ํƒ€๋‚ด๋Š” ์ƒ์ง•๋ฌผ์ด๋‹ค. ๋”ฐ๋ผ์„œ ์šฐ๋ฆฌ๋Š” ํ•œ๋ณต์„ ๋ณด์กดํ•˜๊ณ  ๊ณ„์Šนํ•ด์•ผ ํ•œ๋‹ค.<์ดํ•˜ ์ƒ๋žต>

Citation instructions

Ko-Llama3-Luxia-8B

@article{kollama3luxiamodelcard,
  title={Ko Llama 3 Luxia Model Card},
  author={AILabs@Saltux},
  year={2024},
  url={https://huggingface.co/saltlux/Ko-Llama3-Luxia-8B/blob/main/README.md}
}

Original Llama-3

@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url={https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
Downloads last month
4,863
Safetensors
Model size
8.17B params
Tensor type
BF16
ยท
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for saltlux/Ko-Llama3-Luxia-8B

Adapters
2 models
Finetunes
1 model
Merges
8 models
Quantizations
5 models