⬢github Python · 799 ★ +17 since we first saw it · pushed 6 h ago · Apache-2.0
nokia-applied-research/AnyJev
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
AnyJev is a Python library that converts any LLM into a calibrated decision model without fine-tuning. It wraps language models to produce typed decisions with real probability distributions (e.g. routing a ticket to billing/technical/sales), fixing order-flip instability and improving calibration. It supports multiple levels, vLLM serving, and fitting a lightweight head with as few as 100-500 labels.
Why now: It recently appeared on GitHub trending as one of the most-starred new repos, with an active vLLM integration making calibrated LLM decision endpoints easy to deploy.
Who it is for: ML engineers building LLM-based classification or routing systems who need calibrated probabilities without training a model.
calibrationdecision-modeljevjev-modelllmsystem-onetransformersvllm
Stars over our 46 snapshots: 782 to 799, since 9 h ago.
Where people talked about it
- ⬢github new repos, most starred 11 min ago
- ⬢github new repos, most starred 3 h ago
API: https://socialmediatrends-api.osmike.com/v1/repos/nokia-applied-research/AnyJev