Qevi-2B: A Jev-style finetuned model for image classification

Qevi-2B: A Jev-style finetuned model for image classification Ask it "is there a ladder in this image?" and it returns P(Yes) = 0.97 , not a sentence. In exchange for giving up open-ended answers you get substantially better accuracy on closed questions, calibrated probabilities you can threshold on, and up to ~21x faster inference when asking many questions about one image.

This ProductUpdate is relevant to the technology intelligence record because it involves Cohere, qwen. The source article should remain the factual reference for follow-up coverage.

• Ask it "is there a ladder in this image?" and it returns P(Yes) = 0.97 , not a sentence.
• In exchange for giving up open-ended answers you get substantially better accuracy on closed questions, calibrated probabilities you can threshold on, and up to ~21x faster inference when asking many questions about one image.
• Base Qwen3-VL-2B Qevi-2B Accuracy, in-domain 0.855 0.977 Accuracy, held-out domains 0.745 0.889 Expected Calibration Error, held-out 0.160 0.054 New to this?
• EXPLANATION.md is a short, plain-language walkthrough of how it works and why it is fast.
• Read this before you use it This model must be used through a logit readout, not .generate() .
• All the numbers above are measured by reading the LM-head logits at the position where the model would begin its reply, restricted to the allowed answer tokens.