AD-Styles
/

mini-llava-v3

Image-Text-to-Text

vision-language

Model card Files Files and versions

Commit History

docs: drop "(정직한 명시)" subtitle from §변하지 않은 것

e18f68f
verified

AD-Styles commited on 17 days ago

docs: 3-way intro (한국어 재학습 / 환각 wrapper+OOD / 배포 Slim adapter)

fe6c580
verified

AD-Styles commited on 17 days ago

docs: portfolio-tone rebalance (drop self-deprecating PEFT callout, neutral Slim heading)

abac4e0
verified

AD-Styles commited on 17 days ago

docs: soften OOD claim, name slim as PEFT workaround, clarify VQA scope

ee5e61c
verified

AD-Styles commited on 17 days ago

docs: sync model card with corrected VQAv2 measurement (+2pp v3>v2)

85399b0
verified

AD-Styles commited on 17 days ago

Honest messaging: separate capability gains (Korean, OOD) from deployment optimization (Slim)

62f15c2
verified

AD-Styles commited on 18 days ago

Add v3 slim adapter (1045MB → 8.28MB, no quality loss)

eeaf08c
verified

AD-Styles commited on 18 days ago

Add v3 projector (Korean training, 175 min)

4e4ab0c
verified

AD-Styles commited on 18 days ago

Add v3 model card (Korean + Slim + OOD)

eae11b6
verified

AD-Styles commited on 18 days ago

initial commit

4fbe8cd
verified

AD-Styles commited on 18 days ago