64 Downloads Updated 2 days ago
ollama run aminroudaki/decisio-v3
A Gemma 4 12B tuned for decisio, the open-source server that takes a text and typed questions (yes/no, one choice among options, a score on a scale you define) and returns a probability for every option from one forward pass per question.
It answers closed questions about a text noticeably more accurately than the base model and than the previous tuned 12B. Its probabilities are calibrated: when it says 80%, it is right about 80% of the time, at the temperatures built into these files. On 5,000 held-out questions from the distribution it was trained on it is right 78.8% of the time (base Gemma 4 12B: 67.7%, previous tuned 12B: 71.6%).
| tag | file | size | use it when |
|---|---|---|---|
latest, q8_0 |
Q8_0 | 12.7 GB | you want the closest match to the full-precision model |
q4_k_m |
Q4_K_M | 7.4 GB | memory is tight and a small loss is fine |
Both tags carry decisio’s decision keys and the model’s own temperatures, so the probabilities come out calibrated without extra settings.
Measured on 1,000 held-out questions, same text and same readout, against the merged bf16 weights:
| same top answer | median change in probability | accuracy (bf16: 76.6%) | |
|---|---|---|---|
| Q8_0 | 97.2% | 0.0047 | 76.9% |
| Q4_K_M | 93.6% | 0.0176 | 76.2% (difference -0.4, 90% lower bound -1.5) |
The Q8_0 file is within a hair of full precision. The Q4_K_M file changes the top answer on about one question in sixteen, and its accuracy stays within two points of bf16.
bash
ollama pull aminroudaki/decisio-v3 # the 8-bit file
ollama pull aminroudaki/decisio-v3:q4_k_m # the 4-bit file
`
Then point decisio at the Ollama endpoint; the /v1/systemone route answers with a probability for every option.
Context is set to 8,192 tokens in the Modelfile.
Apache License 2.0, as the base model’s.
Built by Tachara AI Lab.