pplx-decider-v1.1-27b

Derived from Qwen/Qwen3.8-27B, revision
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0, under Apache License 2.0.

Modifications: a 255-option decision readout replaces the generation output
layer. Backbone, vision and readout weights were updated by supervised
fine-tuning. Full-attention layers use noncausal attention; pooling uses the
last token. A separately fitted calibration temperature is stored in
decision_config.json.

This private artifact contains the evaluated native checkpoint and its frozen
source implementation. No affiliation with or endorsement by Qwen is implied.