Decisio-12b-tuned-commit

The Gemma 4 12B tuned as a model that answers typed questions about a state with a probability for every option: the commit flavor. This is google/gemma-4-12B-it (revision 707f0a3b) with a LoRA adapter merged into its weights, served with decisio. It is one of two repositories of the same weights (Decisio-12b-tuned-calibrated and Decisio-12b-tuned-commit); they differ in decision_config.json only.

Serving

uv run python -m decisio.serve.vllm_engine --base tachara-ai/Decisio-12b-tuned-commit

Needs decisio 0.31.0 or later; an older decisio does not know the repository's flavor. A plain request gets the repository's defaults with no flag and no adapter field (shown in /health, systemone.repository_defaults and systemone.flavor): the header layout, the temperatures per question type (yes/no 3.314, score 2.1109, choice 1.8222; choice by number of options 2-10: 2.1317, 11-26: 1.8766, 27-255: 1.7181), the yes/no commit rule. The server is named Decisio-12b-tuned-commit; every flag that differs from the repository is reported as an override. vLLM alone loads the weights as an ordinary Gemma 4 checkpoint but does not apply decisio's prompt layout, option-letter readout, temperatures or commit rule.

What this repository is

The calibrated probabilities, with the yes/no commit rule on top: a yes/no probability strictly between 0.20 and 0.80 is reported at the edge of that band on its own side (0.80 above one half, 0.20 at or below it). The answer never changes, its calibration does.

Weights

bf16. The adapter was merged into the base's weights in fp32 and rounded once to bf16, stochastically with seed 0, by python -m decisio.hub_bf16 merge; the merge keeps 0.999996 of the adapter's change in weight space, and every other tensor is the base's, byte for byte. decision_config.json lists every file by sha256 and the merge facts; SHA256SUMS lists the files of this repository. The temperatures were fitted by minimum log loss per question type and choice band, on the plain readout.

Data

Training data not disclosed. No Decision Index or JevBench evaluation items were used in training or checkpoint selection; the data was decontaminated against both boards' public test sets.

Training included the official training splits of some public benchmarks, used under their licences. No test or evaluation items of those benchmarks were used, and every training row was checked against both boards' public test sets.

Licence

The licence of the base model, Apache License 2.0 (see LICENSE and NOTICE). Gemma 4 is Google's.