ShinDJ's picture
Update README.md
535ce21 verified
|
raw
history blame
7.81 kB
metadata
language:
  - en
  - ko
license: llama3
library_name: transformers
base_model:
  - meta-llama/Meta-Llama-3-8B

Bllossom | Demo | Homepage | Github |

The Bllossom language model is a Korean-English bilingual language model based on the open-source LLama3. It enhances the connection of knowledge between Korean and English. It has the following features:

  • Knowledge Linking: Linking Korean and English knowledge through additional training
  • Vocabulary Expansion: Expansion of Korean vocabulary to enhance Korean expressiveness.
  • Instruction Tuning: Tuning using custom-made instruction following data specialized for Korean language and Korean culture
  • Human Feedback: DPO has been applied
  • Vision-Language Alignment: Aligning the vision transformer with this language model

This model developed by MLPLab at Seoultech, Teddysum and Yonsei Univ

Demo Video

Bllossom-V Demo

Bllossom Demo(Kakao)ใ…คใ…คใ…คใ…คใ…คใ…คใ…คใ…ค

NEWS

  • [2024/04] We released Bllossom v2.0, based on llama-3
  • [2023/12] We released Bllossom-Vision v1.0, based on Bllossom
  • [2023/08] We released Bllossom v1.0, based on llama-2.
  • [2023/07] We released Bllossom v0.7, based on polyglot-ko.
์ €ํฌ ์„œ์šธ๊ณผ๊ธฐ๋Œ€ MLP์—ฐ๊ตฌ์‹ค์—์„œ ํ•œ๊ตญ์–ด-์˜์–ด ์ด์ค‘ ์–ธ์–ด๋ชจ๋ธ์ธ Bllossom์„ ๊ณต๊ฐœํ–ˆ์Šต๋‹ˆ๋‹ค!
 - LLama3-8B ๊ธฐ๋ฐ˜์˜ ๊ฒฝ๋Ÿ‰ํ™”๋œ ์‚ฌ์ด์ฆˆ 
 - ํ•œ๊ตญ์–ด-์˜์–ด ์ง€์‹์—ฐ๊ฒฐ์„ ํ†ตํ•œ ํ•œ๊ตญ์–ด ์ง€์‹ ๊ฐ•ํ™”
 - ํ•œ๊ตญ์–ด ์–ดํœ˜์ถ”๊ฐ€
 - ํ•œ๊ตญ์–ด ๋ฌธํ™”, ์–ธ์–ด๋ฅผ ๊ณ ๋ คํ•œ ์ž์ฒด์ œ์ž‘ ๋ฐ์ดํ„ฐ ๊ธฐ๋ฐ˜ ๋ฏธ์„ธ์กฐ์ •
 - ๊ฐ•ํ™”ํ•™์Šต (DPO)
 - ์‹œ๊ฐ-์–ธ์–ด ๋ชจ๋ธํ™•์žฅ

1. Bllossom์€ ์„œ์šธ๊ณผ๊ธฐ๋Œ€, ํ…Œ๋””์ธ, ์—ฐ์„ธ๋Œ€ ์–ธ์–ด์ž์› ์—ฐ๊ตฌ์‹ค์˜ ์–ธ์–ดํ•™์ž์™€ ํ˜‘์—…ํ•ด ๋งŒ๋“  ์‹ค์šฉ์ฃผ์˜๊ธฐ๋ฐ˜ ์–ธ์–ด๋ชจ๋ธ์ž…๋‹ˆ๋‹ค! ์•ž์œผ๋กœ ์ง€์†์ ์ธ ์—…๋ฐ์ดํŠธ๋ฅผ ํ†ตํ•ด ๊ด€๋ฆฌํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค ๋งŽ์ด ํ™œ์šฉํ•ด์ฃผ์„ธ์š” ๐Ÿ™‚
2. Bllossom70B๋ชจ๋ธ, ์–ดํœ˜ํ™•์žฅ๋ชจ๋ธ, ์‹œ๊ฐ-์–ธ์–ด๋ชจ๋ธ์€ ์ถ”ํ›„ ๊ณต๊ฐœํ•  ์˜ˆ์ •์ž…๋‹ˆ๋‹ค. (๊ถ๊ธˆํ•˜์‹ ๋ถ„์€ ๊ฐœ๋ณ„ ์—ฐ๋ฝ์ฃผ์„ธ์š”, GPU๋งŒ ์ง€์›ํ•ด์ฃผ์‹œ๋ฉด ๋ฌด๋ฃŒ๋กœ ๋“œ๋ฆฝ๋‹ˆ๋‹ค!)
3. Bllossom์€ NAACL2024, LREC-COLING2024 (๊ตฌ๋‘) ๋ฐœํ‘œ๋กœ ์ฑ„ํƒ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
4. ์ข‹์€ ์–ธ์–ด๋ชจ๋ธ ๊ณ„์† ์—…๋ฐ์ดํŠธ ํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค!! ํ•œ๊ตญ์–ด ๊ฐ•ํ™”๋ฅผ์œ„ํ•ด ๊ณต๋™ ์—ฐ๊ตฌํ•˜์‹ค๋ถ„ ์–ธ์ œ๋“  ํ™˜์˜ํ•ฉ๋‹ˆ๋‹ค!!

Example code

Install Dependencies

pip install torch transformers==4.40.0 accelerate

Python code with Pipeline

import transformers
import torch

model_id = "MLP-KTLim/Bllossom"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

pipeline.model.eval()

PROMPT = '''๋‹น์‹ ์€ ์œ ์šฉํ•œ AI ์–ด์‹œ์Šคํ„ดํŠธ์ž…๋‹ˆ๋‹ค. ์‚ฌ์šฉ์ž์˜ ์งˆ์˜์— ๋Œ€ํ•ด ์นœ์ ˆํ•˜๊ณ  ์ •ํ™•ํ•˜๊ฒŒ ๋‹ต๋ณ€ํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.'''
instruction = "์„œ์šธ๊ณผํ•™๊ธฐ์ˆ ๋Œ€ํ•™๊ต MLP์—ฐ๊ตฌ์‹ค์— ๋Œ€ํ•ด ์†Œ๊ฐœํ•ด์ค˜"

messages = [
    {"role": "system", "content": f"{PROMPT}"},
    {"role": "user", "content": f"{instruction}"}
    ]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=2048,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
    repetition_penalty = 1.1
)

print(outputs[0]["generated_text"][len(prompt):])

# ์„œ์šธ๊ณผํ•™๊ธฐ์ˆ ๋Œ€ํ•™๊ต MLP์—ฐ๊ตฌ์‹ค์€ ๋ฉ€ํ‹ฐ๋ชจ๋‹ฌ ์ž์—ฐ์–ด์ฒ˜๋ฆฌ ์—ฐ๊ตฌ๋ฅผ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ๊ตฌ์„ฑ์›์€ ์ž„๊ฒฝํƒœ ๊ต์ˆ˜์™€ ๊น€๋ฏผ์ค€, ๊น€์ƒ๋ฏผ, ์ตœ์ฐฝ์ˆ˜, ์›์ธํ˜ธ, ์œ ํ•œ๊ฒฐ, ์ž„ํ˜„์„, ์†ก์Šน์šฐ, ์œก์ •ํ›ˆ, ์‹ ๋™์žฌ ํ•™์ƒ์ด ์žˆ์Šต๋‹ˆ๋‹ค.

Python code with AutoModel


import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = 'MLP-KTLim/Bllossom'

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

model.eval()

PROMPT = '''๋‹น์‹ ์€ ์œ ์šฉํ•œ AI ์–ด์‹œ์Šคํ„ดํŠธ์ž…๋‹ˆ๋‹ค. ์‚ฌ์šฉ์ž์˜ ์งˆ์˜์— ๋Œ€ํ•ด ์นœ์ ˆํ•˜๊ณ  ์ •ํ™•ํ•˜๊ฒŒ ๋‹ต๋ณ€ํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.'''
instruction = "์„œ์šธ๊ณผํ•™๊ธฐ์ˆ ๋Œ€ํ•™๊ต MLP์—ฐ๊ตฌ์‹ค์— ๋Œ€ํ•ด ์†Œ๊ฐœํ•ด์ค˜"

messages = [
    {"role": "system", "content": f"{PROMPT}"},
    {"role": "user", "content": f"{instruction}"}
    ]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=2048,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
    repetition_penalty = 1.1
)

print(tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True))
# ์„œ์šธ๊ณผํ•™๊ธฐ์ˆ ๋Œ€ํ•™๊ต MLP์—ฐ๊ตฌ์‹ค์€ ๋ฉ€ํ‹ฐ๋ชจ๋‹ฌ ์ž์—ฐ์–ด์ฒ˜๋ฆฌ ์—ฐ๊ตฌ๋ฅผ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ๊ตฌ์„ฑ์›์€ ์ž„๊ฒฝํƒœ ๊ต์ˆ˜์™€ ๊น€๋ฏผ์ค€, ๊น€์ƒ๋ฏผ, ์ตœ์ฐฝ์ˆ˜, ์›์ธํ˜ธ, ์œ ํ•œ๊ฒฐ, ์ž„ํ˜„์„, ์†ก์Šน์šฐ, ์œก์ •ํ›ˆ, ์‹ ๋™์žฌ ํ•™์ƒ์ด ์žˆ์Šต๋‹ˆ๋‹ค.

Citation

Language Model

@misc{bllossom,
  author = {ChangSu Choi, Yongbin Jeong, Seoyoon Park, InHo Won, HyeonSeok Lim, SangMin Kim, Yejee Kang, Chanhyuk Yoon, Jaewan Park, Yiseul Lee, HyeJin Lee, Younggyun Hahm, Hansaem Kim, KyungTae Lim},
  title = {Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Korean},
  year = {2024},
  journal = {LREC-COLING 2024},
  paperLink = {\url{https://arxiv.org/pdf/2403.10882}},
 },
}

Vision-Language Model

@misc{bllossom-V,
  author = {Dongjae Shin, Hyunseok Lim, Inho Won, Changsu Choi, Minjun Kim, Seungwoo Song, Hangyeol Yoo, Sangmin Kim, Kyungtae Lim},
  title = {X-LLaVA: Optimizing Bilingual Large Vision-Language Alignment},
  year = {2024},
  publisher = {GitHub},
  journal = {NAACL 2024 findings},
  paperLink = {\url{https://arxiv.org/pdf/2403.11399}},
 },
}

Contact

Contributor