FinShibainu Model Card

๋ชจ๋ธ์€ KRX LLM ๊ฒฝ์ง„๋Œ€ํšŒ ๋ฆฌ๋”๋ณด๋“œ์—์„œ ์šฐ์ˆ˜์ƒ์„ ์ˆ˜์ƒํ•œ shibainu24 ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค. ๋ชจ๋ธ์€ ๊ธˆ์œต, ํšŒ๊ณ„ ๋“ฑ ๊ธˆ์œต๊ด€๋ จ ์ง€์‹์— ๋Œ€ํ•œ Text Generation์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.

๋ฐ์ดํ„ฐ์…‹ ์ˆ˜์ง‘ ๋ฐ ํ•™์Šต์— ๊ด€๋ จ๋œ ์ฝ”๋“œ๋Š” https://github.com/aiqwe/FinShibainu์— ์ž์„ธํ•˜๊ฒŒ ๊ณต๊ฐœ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.

Usage

https://github.com/aiqwe/FinShibainu์˜ example์„ ์ฐธ์กฐํ•˜๋ฉด ์‰ฝ๊ฒŒ inference๋ฅผ ํ•ด๋ณผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ๋Œ€๋ถ€๋ถ„์˜ Inference๋Š” RTX-3090 ์ด์ƒ์—์„œ ๋‹จ์ผ GPU ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค.

pip install vllm
import pandas as pd
from vllm import LLM

inputs = [
    "์™ธํ™˜์‹œ์žฅ์—์„œ ์ผ๋ณธ ์—”ํ™”์™€ ๋ฏธ๊ตญ ๋‹ฌ๋Ÿฌ์˜ ํ™˜์œจ์ด ๋‘ ์‹œ์žฅ์—์„œ ์•ฝ๊ฐ„์˜ ์ฐจ์ด๋ฅผ ๋ณด์ด๊ณ  ์žˆ๋‹ค. ์ด๋•Œ ๋ฌด์œ„ํ—˜ ์ด์ต์„ ์–ป๊ธฐ ์œ„ํ•œ ์ ์ ˆํ•œ ๊ฑฐ๋ž˜ ์ „๋žต์€ ๋ฌด์—‡์ธ๊ฐ€?",
    "์‹ ์ฃผ์ธ์ˆ˜๊ถŒ๋ถ€์‚ฌ์ฑ„(BW)์—์„œ ์ฑ„๊ถŒ์ž๊ฐ€ ์‹ ์ฃผ์ธ์ˆ˜๊ถŒ์„ ํ–‰์‚ฌํ•˜์ง€ ์•Š์„ ๊ฒฝ์šฐ ์–ด๋–ค ์ผ์ด ๋ฐœ์ƒํ•˜๋Š”๊ฐ€?",
    "๊ณต๋งค๋„(Short Selling)์— ๋Œ€ํ•œ ์„ค๋ช…์œผ๋กœ ์˜ณ์ง€ ์•Š์€ ๊ฒƒ์€ ๋ฌด์—‡์ž…๋‹ˆ๊นŒ?"
]

llm = LLM(model="aiqwe/krx-llm-competition", tensor_parallel_size=1)
sampling_params = SamplingParams(temperature=0.7, max_tokens=128)
outputs = llm.generate(inputs, sampling_params)
for o in outputs:
    print(o.prompt)
    print(o.outputs[0].text)
    print("*"*100)

Model Card

Contents Spec
Base model Qwen2.5-7B-Instruct
dtype bfloat16
PEFT LoRA (r=8, alpha=64)
Learning Rate 1e-5 (varies by further training)
LRScheduler Cosine (warm-up: 0.05%)
Optimizer AdamW
Distributed / Efficient Tuning DeepSpeed v3, Flash Attention

Datset Card

Reference ๋ฐ์ดํ„ฐ์…‹์€ ์ผ๋ถ€ ์ €์ž‘๊ถŒ ๊ด€๊ณ„๋กœ ์ธํ•ด Link๋กœ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. MCQA์™€ QA ๋ฐ์ดํ„ฐ์…‹์€ https://huggingface.co/datasets/aiqwe/FinShibainu์œผ๋กœ ๊ณต๊ฐœํ•ฉ๋‹ˆ๋‹ค.
๋˜ํ•œ https://github.com/aiqwe/FinShibainu๋ฅผ ์ด์šฉํ•˜๋ฉด ๋‹ค์–‘ํ•œ ์œ ํ‹ธ๋ฆฌํ‹ฐ ๊ธฐ๋Šฅ์„ ์ œ๊ณตํ•˜๋ฉฐ, ๋ฐ์ดํ„ฐ ์†Œ์‹ฑ Pipeline์„ ์ฐธ์กฐํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

References

๋ฐ์ดํ„ฐ๋ช… url
ํ•œ๊ตญ์€ํ–‰ ๊ฒฝ์ œ๊ธˆ์œต ์šฉ์–ด 700์„  Link
์žฌ๋ฌดํšŒ๊ณ„ ํ•ฉ์„ฑ ๋ฐ์ดํ„ฐ ์ž์ฒด ์ œ์ž‘
๊ธˆ์œต๊ฐ๋…์šฉ์–ด์‚ฌ์ „ Link
web-text.synthetic.dataset-50k Link
์ง€์‹๊ฒฝ์ œ์šฉ์–ด์‚ฌ์ „ Link
ํ•œ๊ตญ๊ฑฐ๋ž˜์†Œ ๋น„์ •๊ธฐ ๊ฐ„ํ–‰๋ฌผ Link
ํ•œ๊ตญ๊ฑฐ๋ž˜์†Œ๊ทœ์ • Link
์ดˆ๋ณดํˆฌ์ž์ž ์ฆ๊ถŒ๋”ฐ๋ผ์žก๊ธฐ Link
์ฒญ์†Œ๋…„์„ ์œ„ํ•œ ์ฆ๊ถŒํˆฌ์ž Link
๊ธฐ์—…์‚ฌ์—…๋ณด๊ณ ์„œ ๊ณต์‹œ์ž๋ฃŒ Link
์‹œ์‚ฌ๊ฒฝ์ œ์šฉ์–ด์‚ฌ์ „ Link

MCQA

MCQA ๋ฐ์ดํ„ฐ๋Š” Reference๋ฅผ ๊ธฐ๋ฐ˜์œผ๋กœ ๋‹ค์ง€์„ ๋‹คํ˜• ๋ฌธ์ œ๋ฅผ ์ƒ์„ฑํ•œ ๋ฐ์ดํ„ฐ์…‹์ž…๋‹ˆ๋‹ค. ๋ฌธ์ œ์™€ ๋‹ต ๋ฟ๋งŒ ์•„๋‹ˆ๋ผ Reasoning ํ…์ŠคํŠธ๊นŒ์ง€ ์ƒ์„ฑํ•˜์—ฌ ํ•™์Šต์— ์ถ”๊ฐ€ํ•˜์˜€์Šต๋‹ˆ๋‹ค.
ํ•™์Šต์— ์‚ฌ์šฉ๋œ ๋ฐ์ดํ„ฐ๋Š” ์•ฝ 4.5๋งŒ๊ฐœ ๋ฐ์ดํ„ฐ์…‹์ด๋ฉฐ, tiktoken์˜ o200k_base(gpt-4o, gpt-4o-mini Tokenizer)๋ฅผ ๊ธฐ์ค€์œผ๋กœ ์ด 2์ฒœ๋งŒ๊ฐœ์˜ ํ† ํฐ์œผ๋กœ ํ•™์Šต๋˜์—ˆ์Šต๋‹ˆ๋‹ค.

๋ฐ์ดํ„ฐ๋ช… ๋ฐ์ดํ„ฐ ์ˆ˜ ํ† ํฐ ์ˆ˜
ํ•œ๊ตญ์€ํ–‰ ๊ฒฝ์ œ๊ธˆ์œต ์šฉ์–ด 700์„  1,203 277,114
์žฌ๋ฌดํšŒ๊ณ„ ๋ชฉ์ฐจ๋ฅผ ์ด์šฉํ•œ ํ•ฉ์„ฑ๋ฐ์ดํ„ฐ 451 99,770
๊ธˆ์œต๊ฐ๋…์šฉ์–ด์‚ฌ์ „ 827 214,297
hf_web_text_synthetic_dataset_50k 25,461 7,563,529
์ง€์‹๊ฒฝ์ œ์šฉ์–ด์‚ฌ์ „ 2,314 589,763
ํ•œ๊ตญ๊ฑฐ๋ž˜์†Œ ๋น„์ •๊ธฐ ๊ฐ„ํ–‰๋ฌผ 1,183 230,148
ํ•œ๊ตญ๊ฑฐ๋ž˜์†Œ๊ทœ์ • 3,015 580,556
์ดˆ๋ณดํˆฌ์ž์ž ์ฆ๊ถŒ๋”ฐ๋ผ์žก๊ธฐ 599 116,472
์ฒญ์†Œ๋…„์„ ์œ„ํ•œ ์ฆ๊ถŒ ํˆฌ์ž 408 77,037
๊ธฐ์—…์‚ฌ์—…๋ณด๊ณ ์„œ ๊ณต์‹œ์ž๋ฃŒ 3,574 629,807
์‹œ์‚ฌ๊ฒฝ์ œ์šฉ์–ด์‚ฌ์ „ 7,410 1,545,842
ํ•ฉ๊ณ„ 46,445 19,998,931

QA

QA ๋ฐ์ดํ„ฐ๋Š” Reference์™€ ์งˆ๋ฌธ์„ ํ•จ๊ป˜ Input์œผ๋กœ ๋ฐ›์•„ ์ƒ์„ฑํ•œ ๋‹ต๋ณ€๊ณผ Reference ์—†์ด ์งˆ๋ฌธ๋งŒ์„ Input์œผ๋กœ ๋ฐ›์•„ ์ƒ์„ฑํ•œ ๋‹ต๋ณ€ 2๊ฐ€์ง€๋กœ ๊ตฌ์„ฑ๋ฉ๋‹ˆ๋‹ค.
Reference๋ฅผ ์ œ๊ณต๋ฐ›์œผ๋ฉด ๋ชจ๋ธ์€ ๋ณด๋‹ค ์ •ํ™•ํ•œ ๋‹ต๋ณ€์„ ํ•˜์ง€๋งŒ ๋ชจ๋ธ๋งŒ์˜ ์ง€์‹์ด ์ œํ•œ๋˜์–ด ๋‹ต๋ณ€์ด ์ข€๋” ์งง์•„์ง€๊ฑฐ๋‚˜ ๋‹ค์–‘์„ฑ์ด ์ค„์–ด๋“ค๊ฒŒ ๋ฉ๋‹ˆ๋‹ค. ์ด 4.8๋งŒ๊ฐœ์˜ ๋ฐ์ดํ„ฐ์…‹๊ณผ 2์–ต๊ฐœ์˜ ํ† ํฐ์œผ๋กœ ํ•™์Šต๋˜์—ˆ์Šต๋‹ˆ๋‹ค.

๋ฐ์ดํ„ฐ๋ช… ๋ฐ์ดํ„ฐ ์ˆ˜ ํ† ํฐ ์ˆ˜
ํ•œ๊ตญ์€ํ–‰ ๊ฒฝ์ œ๊ธˆ์œต ์šฉ์–ด 700์„  1,023 846,970
๊ธˆ์œต๊ฐ๋…์šฉ์–ด์‚ฌ์ „ 4,128 3,181,831
์ง€์‹๊ฒฝ์ œ์šฉ์–ด์‚ฌ์ „ 6,526 5,311,890
ํ•œ๊ตญ๊ฑฐ๋ž˜์†Œ ๋น„์ •๊ธฐ ๊ฐ„ํ–‰๋ฌผ 1,510 1,089,342
ํ•œ๊ตญ๊ฑฐ๋ž˜์†Œ๊ทœ์ • 4,858 3,587,059
๊ธฐ์—…์‚ฌ์—…๋ณด๊ณ ์„œ ๊ณต์‹œ์ž๋ฃŒ 3,574 629,807
์‹œ์‚ฌ๊ฒฝ์ œ์šฉ์–ด์‚ฌ์ „ 29,920 5,981,839
ํ•ฉ๊ณ„ 47,965 199,998,931

Citation

@misc{jaylee2024finshibainu,
  author = {Jay Lee},
  title = {FinShibainu: Korean specified finance model},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  url = {https://github.com/aiqwe/FinShibainu}
}
Downloads last month
82
Safetensors
Model size
7.62B 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 aiqwe/FinShibainu

Base model

Qwen/Qwen2.5-7B
Finetuned
(151)
this model
Quantizations
2 models

Dataset used to train aiqwe/FinShibainu