JevAny: train and deploy decision models across backbones

A training and deployment library adapts language-model backbones to typed decisions with learned pointer heads or direct option-token readouts. It publishes LoRA checkpoints, data preparation, calibration and evaluation tools alongside an archived application replay gallery.

Notes

The author describes training on 2,180,242 labelled decisions and publishes Gemma 4B, Qwen 4B and 27B, and Muse 30B adapters; base weights are loaded separately.

source-backed — Public repository, docs or live artifact. About this label

Destinations

Availability & demo checks

Report a problem →

Also linked

• JevAny Qwen 27B adapter ↗

Filed under

• #local
• #training
• #evaluation
• #decision-making

In collections

• Benchmarks & independent tests →
• Local & replica models →