« BackGLiNER2: Unified Schema-Based Information Extractiongithub.comSubmitted by apwheele 6 hours ago
  • iwhalen 3 hours ago

    Very cool stuff. Love the focus on CPU-first.

    Would also love to see some throughput numbers on basic VM setup.

    Edit: there are some latency numbers in the paper https://arxiv.org/pdf/2507.18546

    • deepsquirrelnet 3 hours ago

      Zero-shot encoder models are so cool. I'll definitely be checking this out.

      If you're looking for a zero-shot classifier, tasksource is in a similar vein.

      https://huggingface.co/tasksource/ModernBERT-large-nli

      • hbcondo714 4 hours ago

        There is another version at:

        https://github.com/urchade/GLiNER

        Looks like it’s still being maintained too?