You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

LLaMA 3.1 8B Korean Food Fine-Tuned Model

์ด ๋ชจ๋ธ์€ Meta์˜ LLaMA 3.1 8B๋ฅผ ๊ธฐ๋ฐ˜์œผ๋กœ ํ•œ๊ตญ ์Œ์‹ ๊ด€๋ จ ๋ฐ์ดํ„ฐ์…‹์œผ๋กœ ํŒŒ์ธํŠœ๋‹ํ•œ ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค.
Hugging Face์˜ peft ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ํšจ์œจ์ ์œผ๋กœ ํ›ˆ๋ จ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.

๐Ÿ“Œ Model Details

  • Developed by: SGT-Cho
  • Dataset: ํ•œ๊ตญ ์Œ์‹ ๊ด€๋ จ ๋ฐ์ดํ„ฐ์…‹
  • Fine-tuned from: LLaMA 3.1 8B
  • Training Method: LoRA (peft)
  • Language(s): Korean (ko)
  • License: Apache 2.0

๐Ÿ“œ Model Sources

https://huggingface.co/meta-llama/Llama-3.1-8B

๐ŸŽฏ Intended Use

์ด ๋ชจ๋ธ์€ ํ•œ๊ตญ ์Œ์‹ ๊ด€๋ จ ์งˆ์˜์‘๋‹ต, ์š”๋ฆฌ๋ฒ• ์ถ”์ฒœ, ์‹์žฌ๋ฃŒ ์„ค๋ช… ๋“ฑ์˜ ์ž‘์—…์— ์ตœ์ ํ™”๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.

โœ… Direct Use

  • ํ•œ๊ตญ ์Œ์‹ ๊ด€๋ จ ์ฑ—๋ด‡
  • ๋ ˆ์‹œํ”ผ ์ถ”์ฒœ ์‹œ์Šคํ…œ
  • ์‹๋‹น ๋ฆฌ๋ทฐ ๋ถ„์„

๐Ÿ”ง Downstream Use

  • ๋‹ค๋ฅธ ๋„๋ฉ”์ธ(์˜ˆ: ํ•œ์‹ ์š”๋ฆฌ๋ฒ• ์ƒ์„ฑ, ๋ฉ”๋‰ด ์ถ”์ฒœ)์œผ๋กœ ์ถ”๊ฐ€์ ์ธ ํŒŒ์ธํŠœ๋‹ ๊ฐ€๋Šฅ

โš ๏ธ Limitations & Biases

  • ์ด ๋ชจ๋ธ์€ ํŠน์ • ํ•œ๊ตญ ์Œ์‹ ๊ด€๋ จ ๋ฐ์ดํ„ฐ์…‹์„ ๊ธฐ๋ฐ˜์œผ๋กœ ํ›ˆ๋ จ๋˜์–ด ์žˆ์–ด ์ผ๋ฐ˜์ ์ธ ํ•œ๊ตญ์–ด ์ดํ•ด๋ ฅ์€ ์›๋ณธ LLaMA 3.1๋ณด๋‹ค ๋‚ฎ์„ ์ˆ˜ ์žˆ์Œ.
  • ํŠน์ • ์Œ์‹์— ๋Œ€ํ•œ ์„ค๋ช…์ด ํŽธํ–ฅ๋  ๊ฐ€๋Šฅ์„ฑ์ด ์žˆ์Œ.

๐Ÿ›  How to Use

Hugging Face transformers ๋ฐ peft๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๋ชจ๋ธ์„ ๋กœ๋“œํ•˜๋Š” ์˜ˆ์ œ์ž…๋‹ˆ๋‹ค.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "mobilelife/llama3.1_8b_korean_food_finetuned"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

input_text = "๋ถˆ๊ณ ๊ธฐ ์š”๋ฆฌ๋ฅผ ์œ„ํ•œ ์žฌ๋ฃŒ๋Š” ๋ฌด์—‡์ธ๊ฐ€์š”?"
inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))



@misc{llama3_korean_food,
  title={LLaMA 3.1 8B Korean Food Fine-Tuned Model},
  author={Minjae Cho},
  year={2025},
  url={https://huggingface.co/mobilelife/llama3.1_8b_korean_food_finetuned}
}
Downloads last month
0
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Dataset used to train SGTCho/llama3.1_8b_korean_food_finetuned