This is an open-source multimodal model for vision question answering, distributed via Hugging Face. It is designed for AI researchers and developers who need a CLI-accessible model for answering questions about images and text. The model supports integration into custom research pipelines.
Vqa Rlvr Sft 8b is an Other AI product. It focuses on enabling researchers to perform vision question answering on multimodal data using an open-source model. It is built as an open-source project for ai researchers and developers. Vqa Rlvr Sft 8b is open source under the Apache-2.0 license. The product ships for the web and the command line.
omnifish123 builds and maintains Vqa Rlvr Sft 8b, 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-8b verified by the PulseGate indexer
