Nokia Open-Sources AnyJev: A Training-Free Layer That Turns Any Open LLM Into a Calibrated Decision Model
Nokia open-sources AnyJev: turn any open LLM into a calibrated classifier without retraining. PyPI-ready, Apache-2.0.
Why it matters
A practical, deployment-ready layer for a common production pattern — classification over generation — that practitioners can drop into existing LLM stacks immediately. No fine-tuning required.
The key facts
14 to knowAnyJev: training-free layer for LLM-based classification
Open-source, Apache-2.0 license
Available on PyPI for immediate deployment
Works with any open LLM via transformers library
Addresses production use case: fixed-set decision selection vs. generation
Calibrated output (probability/confidence scores implied)
Nokia applied research team contribution
AnyJev: open-source Python library, Apache-2.0 license
Training-free layer for open LLMs
Targets classification/selection tasks (picking one answer from fixed set)
Available on PyPI with transformers integration
Calibrated decision model output
No retraining required
Published by Nokia applied research team
Go to the source
MarkTechPostmarktechpost.com
Publisher excerpt: Nokia’s applied research team has open-sourced AnyJev, a Python library that turns an open LLM into a decision model. It needs no training. It targets a common production job: picking one answer from a fixed set instead of writing a sentence. Is it deployable? Yes, it installs from PyPI, ships…
