[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源多模态对话模型
image-classification
gpt
multi-modal
semantic-segmentation
video-classification
mme
image-text-retrieval
llm
vision-language-model
gpt-4v
vit-6b
vit-22b
gpt-4o
-
Updated
Jun 12, 2024 - Python