LLaVA 1.5
University of Wisconsin MadisonMicrosoft ResearchChatQuestion answeringVisual question answeringOpen weights
The LLaVA 1.5 model is an open-weights chat model from University of Wisconsin Madison,Microsoft Research with 13000000000.0 parameters.
About LLaVA 1.5
Large multimodal models (LMM) have recently shown encouraging progress with visual instruction tuning. In this note, we show that the fully-connected vision-language cross-modal connector in LLaVA is surprisingly powerful and data-efficient. With sim
Details
- Provider
- University of Wisconsin Madison,Microsoft Research
- Task
- Chat,Question answering,Visual question answering
- Parameters
- 13000000000.0
- Released
- 2023-11-05
- Open weights
- Yes