10,2 ΡΡΡ ΠΏΠΎΠ΄ΠΏΠΈΡΡΠΈΠΊΠΎΠ²
π¦ LLaVA: Large Language and Vision Assistant
LLaVA - Π½ΠΎΠ²Π°Ρ ΠΊΠΎΠΌΠΏΠ»Π΅ΠΊΡΠ½Π°Ρ ΠΌΡΠ»ΡΡΠΈΠΌΠΎΠ΄Π°Π»ΡΠ½Π°Ρ ΠΌΠΎΠ΄Π΅Π»Ρ, ΠΊΠΎΡΠΎΡΠ°Ρ ΠΏΠΎΠ΄ΡΠΎΠ±Π½ΠΎ ΠΎΠ±ΡΡΡΠ½ΠΈΡ Π»ΡΠ±ΠΎΠ΅ ΠΈΠ·ΠΎΠ±ΡΠ°ΠΆΠ΅Π½ΠΈΠ΅
git clone https://github.com/haotian-liu/LLaVA.git
cd LLaVA
π₯ Github: https://github.com/haotian-liu/LLaVA
π Paper: https://arxiv.org/pdf/2309.09958v1.pdf
βοΈ Datasets: https://paperswithcode.com/dataset/mmlu
ΠΠΊΠΎΠ»ΠΎ ΠΌΠΈΠ½ΡΡΡ
19Β ΡΠ΅Π½ΡΡΠ±ΡΡΒ 2023