Beta

Explore
Marketplace
Neural Labs
Chat
Wallet
Docs

Beta

Explore Marketplace Neural Labs Wallet Docs

Build

Manage

My assets Manage wallet Organization

Community

Discord X (Twitter)Telegram

Docs Privacy Policy Terms and Conditions

Proud member of

Proud member of

Docs Cookie Policy

Privacy Policy Terms and Conditions

© 2026 AlphaNeural AI. All rights reserved.

korean-stock-news-qwen-3b-lora – AI Model by 3kd1000 | AlphaNeural AI

You can deploy this model and start earning money today!

3kd1000/
korean-stock-news-qwen-3b-lora

like

0

text-generation

Qwen/Qwen2.5-3B-Instruct

Views

No views yet

Korean Stock News Qwen 3B LoRA

모델 개요

한국 주식 뉴스 분석을 위해 Qwen2.5-3B-Instruct를 파인튜닝한 LoRA 모델입니다.

주요 기능

📰 뉴스 카테고리 분류 (domestic_direct/global_related/macro_economic/geopolitical/irrelevant)
📊 주식시장 영향도 분석
🏢 관련 기업 추출
💹 투자 추천 생성

성능

Base Model: Qwen2.5-3B-Instruct
Training Time: 37분 (345배 성능 향상)
Token Accuracy: 79%
Training Loss: 0.98

사용법

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# 베이스 모델 로드
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")

# LoRA 어댑터 적용
model = PeftModel.from_pretrained(base_model, "3kd1000/3kd1000/korean-stock-news-qwen-3b-lora")

학습 환경

GPU: AMD RX 9070 XT (16GB VRAM)
CPU: AMD 9800X3D
RAM: 32GB
OS: WSL2 Ubuntu 22.04.5 LTS
Framework: Transformers + PEFT + TRL

라이선스

Apache 2.0

제작자

정주상 (jsjung)