Peacock presents a comprehensive suite of Arabic MLLMs, Peacock models outperform multilingual baseline mBlip, Pretraining data is curated from publicly available English datasets translated into Arabic, Models trained in two stages - pretraining and instruction finetuning, Peacock models excel in VQA tasks on various datasets, Henna benchmark evaluates model capabilities related to Arabic culture.
לשפה אחרת
מתוכן המקור
arxiv.org
תובנות מפתח מזוקקות מ:
by Fakhraddin A... ב- arxiv.org 03-05-2024
https://arxiv.org/pdf/2403.01031.pdfשאלות מעמיקות