InternVL2-8B is an open-weight 8 billion parameter multimodal model developed by OpenGVLab. It processes both images and text, supporting tasks such as visual question answering, image captioning, and document understanding. The model is distributed on Hugging Face with Transformers compatibility and a chat template, making it suitable for researchers and developers building multimodal AI applications.
InternVL2 8B is a Foundation models & chat project. It focuses on performing advanced vision-language tasks such as image captioning, visual question answering, and multimodal reasoning without relying on closed-source APIs. It is built as an open-source project for developers. The project is open source (MIT). It ships for the web, the command line, and API.
It is developed by OpenGVLab, and it first shipped in 2023. The project is developed in the open on GitHub with 10.1k stars. It operates in a well-populated space: PulseGate tracks 12 similar projects. Among its 4 catalogued features are image-text-to-text, multimodal understanding, and transformers compatible.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do