The Fine-Tuning Index / Fine-Tuning Tools / #65
haotian-liu/LLaVA
by haotian-liu · Fine-Tuning Tools · updated 2y ago
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
49
momentum
25,078
stars
2,773
forks
#65
rank
chatbotchatgptfoundation-modelsgpt-4instruction-tuningllamallama-2llama2llavamulti-modalitymultimodalvision-language-model
View on GitHub →