This open-source model supports vision question answering on multimodal data, such as images and text, for AI research and development. Distributed via Hugging Face, it is accessible via CLI and can be integrated into custom research pipelines.
Vqa Rlvr Sft 2b sits in PulseGate's Other AI category. It focuses on providing researchers with a model for answering questions about images and text using open-source tools. It is built as an open-source project for ai researchers and developers. Vqa Rlvr Sft 2b is open source under the Apache-2.0 license. Vqa Rlvr Sft 2b is available on the web and the command line.
It is developed by omnifish123, and the product first shipped in 2026. Development happens publicly on GitHub with 49 commits in the last 90 days. Key capabilities include vision question answering, multimodal input, and open source weights.
Latest indexed changes and source events
omnifish123/vqa-rlvr-sft-2b verified by the PulseGate indexer
Other apps tracked under the same category.
