ModelPrésentéExterne

KoBEiT3

Base Model : beit3largeindomainpatch16224 ( best epoch : 8 learning rate : 2e-5 fixed seed : 42

Sourcehuggingface.co/SeanForHim/KoBEiT3/tree/3e383ca39e5d67e742d8bfe59b7caa4b86a6ac25

TypeOtherVersionRevision 3e383ca

Source du modèle

Type: Other
Taille du fichier: 7,91 GB
Version: vRevision 3e383ca
Mis à jour: 26 sept. 2026
Téléchargements: 0
Tâches: Légendes
Source: Hugging Face

Description de la source

BEiT3 based Korean VQA Model # (https://github.com/SeanJeonghwanLee/KoBEiT3)

Basic information

Model

Sources

1 source

Hugging FacePrincipalVersion 3e383ca39e5d67e742d8bfe59b7caa4b86a6ac25

huggingface.co/SeanForHim/KoBEiT3/tree/3e383ca39e5d67e742d8bfe59b7caa4b86a6ac25

Vérifié 11 sept.

Artefacts du modèle

1 artefact

checkpoint-best.pth

pth · 7,91 GB · SHA-256 a7141c4e4712…9861 · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme11 sept.huggingface.co/SeanForHim/KoBEiT3

--- license: mit language: - ko pipeline_tag: visual-question-answering tags: - beit3 --- # BEiT3 based Korean VQA Model # (https://github.com/SeanJeonghwanLee/KoBEiT3) ## Basic information ## ### Model ### - Base Model : beit3_large_indomain_patch16_224 (https://github.com/microsoft/unilm/tree/master/beit3) - best epoch : 8 - learning rate : 2e-5 - fixed seed : 42 - Tokenizer - korean sentencepiece tokenizer trained on korean wikipedia ### Dataset ### - KoBEiT3 - aihub 시각정보 기반 질의응답 (https://aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=realm&dataSetSn=104) * Only Korean can access to the dataset - Tokenizer - kowiki-latest-pages-articles.xml.bz2 (https://dumps.wikimedia.org/kowiki/latest/)