CogVLM-17B
Tsinghua UniversityZ.ai (Zhipu AI)Beihang UniversityImage captioningVisual question answeringChatOpen weights
The CogVLM-17B model is an open-weights image captioning model from Tsinghua University,Z.ai (Zhipu AI),Beihang University with 17000000000.0 parameters.
About CogVLM-17B
We introduce CogVLM, a powerful open-source visual language foundation model. Different from the popular shallow alignment method which maps image features into the input space of language model, CogVLM bridges the gap between the frozen pretrained l
Details
- Provider
- Tsinghua University,Z.ai (Zhipu AI),Beihang University
- Task
- Image captioning,Visual question answering,Chat
- Parameters
- 17000000000.0
- Released
- 2023-11-06
- Open weights
- Yes