Skip to content

jwg0830

EXAONE-Deep-7.8B-sft_v0_2

jwg0830/EXAONE-Deep-7.8B-sft_v0_2

EXAONE-Deep-7.8B-sft_v0_2 is a text generation model from jwg0830. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.

LGAI-EXAONE/EXAONE-Deep-7.8B를 기반으로, AI Hub 한국어 데이터를 활용해 K-AI 리더보드 5개 벤치마크 (KMMLU-Pro / CLIcK / HLE(Ko) / MuSR(Ko) / Com2-main(Ko))와 유사한 자체 proxy 벤치마크에서 진단한 출력 형식 결손과 Com2-main(Ko) 축의 인과관계 추론 콘텐츠 결손을 함께 교정하기 위해 LoRA 파인…

Downloads · 30 days

11

3% of all-time downloads

All-time downloads

346

Public

Parameters

7.8B

15.6 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors15.6 GB · 100%

At a glance

Task
Text Generation
Library
transformers
License
other
Model type
exaone
Access
Public
Created
Aug 17, 2026
Updated
Aug 17, 2026
SHA
703059d9

Base models

Task
Text Generation
Library
transformers
Type
exaone
License
other
Languages
ko
Created
Aug 17, 2026
Updated
Aug 17, 2026