| --- |
| license: apache-2.0 |
| base_model: google/diffusiongemma-26B-A4B-it |
| base_model_relation: finetune |
| pipeline_tag: text-classification |
| tags: [jev, systemone, typed-decisions, decision-model, diffusion-lm, calibration, nvfp4] |
| --- |
| # super-decider |
|
|
| **What it does.** Given a state (text, JSON or images) and typed questions, the model returns one calibrated answer per |
| question in a single read: `choice` (a probability per option), `noul` (P(yes)) and `score` (expected level over an |
| ordered rubric, with the distribution). |
|
|
| ## Model |
| - **Base:** `google/diffusiongemma-26B-A4B-it` (discrete-diffusion MoE, 26B total, 4B active), served from NVIDIA's |
| NVFP4 checkpoint `nvidia/diffusiongemma-26B-A4B-it-NVFP4`. |
| - 18 GB NVFP4 checkpoint (experts 4-bit). No benchmark test items were used for training. |
| - `generation_config.json` sets `confidence_threshold` 0.3 for thought canvases. |
| - Served with contexts up to 131,072 tokens. |
|
|
| ## How it works |
| - **Fine-tuned for decisions.** DiffusionGemma 26B-A4B is fine-tuned on permissively licensed and synthetic decision |
| data, then merged into NVIDIA's NVFP4 checkpoint. |
| - **One-step reads.** All answer slots of a request are filled in one denoising step, so several questions cost little |
| more than one. |
| - **Bidirectional attention within each question.** The prompt block of every question is read in both directions, not |
| only left to right. The model was trained this way, and the runtime applies the same attention through a small vLLM |
| patch (`DJEV_BIDIR_SERVE=1`, `DJEV_BIDIR=qsep`). |
| - **Adaptive thinking.** When the model is unsure of an answer, it writes a short thought and reads the answer again. |
| A request can turn this off, keep it on under load, or think on every question with `"thinking"` (see |
| [API docs](https://github.com/Singularity-Compute/super-decider/blob/main/docs/API.md)). |
|
|
| ## Serving |
| Runtime: [Singularity-Compute/super-decider](https://github.com/Singularity-Compute/super-decider) (pinned vLLM nightly, |
| vLLM patches and a structured server). It accepts the Jev / System One request format (`POST /v1/systemone`) and |
| OpenAI-compatible chat completions. One 48 GB GPU is enough; on L40S the NVFP4 weights run through the Marlin W4A16 |
| kernel. |
|
|
| ## Limitations |
| - Answers can change when the input changes in ways that keep its meaning, such as JSON key order or option order. |
| - The model is sometimes confidently wrong on multi-step date and money calculations; thinking on every question fixes |
| part of them. |
| - The training data is English-centric. Images go through the base model's vision path without image fine-tuning. |
|
|
| ## Licence |
| Apache-2.0, like the base model. See [NOTICE.md](NOTICE.md). |
|
|
