Nokia Open-Sources AnyJev: A Training-Free Layer That Turns Any Open LLM Into a Calibrated Decision Model

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.

Deployment and Licensing

Is it deployable? Yes, it installs from PyPI, ships under Apache-2.0, and has transformers support.

Key Characteristics

• Training-free: AnyJev requires no training.
• Decision-focused: It targets picking one answer from a fixed set rather than generating a sentence.
• Calibrated decision model: It turns any open LLM into a calibrated decision model.
• Distribution: It installs from PyPI.
• License: It ships under Apache-2.0.
• Compatibility: It has transformers support.