decider-2b (Verdict-ready)
The decider-2b System One decision model (Qwen3.5-2B-Base, 1.9B parameters, 32768-token context, checkpoint revision v11 — the vendor's default), packaged for Verdict — a high-performance serving engine for System One decision models. Serve it with one command:
# GPU host
docker run --rm --gpus all -p 8080:8080 \
-v ~/.cache/verdict:/root/.cache/verdict \
sgyaqing/verdict:latest-cuda serve verdict-models/decider-2b --host 0.0.0.0
# ModelScope:
docker run --rm --gpus all -p 8080:8080 \
-e VERDICT_USE_MODELSCOPE=1 \
-v ~/.cache/verdict:/root/.cache/verdict \
sgyaqing/verdict:latest-cuda serve sgyaqing/decider-2b --host 0.0.0.0
Endpoints: the standard decision protocols POST /v1/systemone and POST /v1/decisions, native POST /v1/choice | /v1/score | /v1/noul, plus an OpenAI-compatible layer (/v1/chat/completions, /v1/models).
Files
| File | Purpose |
|---|---|
model.json |
manifest: budgets, calibration temperatures, checkpoint declaration |
tokenizer/tokenizer.json (+ tokenizer_config.json) |
the tokenizer |
SHA256SUMS |
checksums for the files above |
checkpoint (config.json, model.safetensors, generation_config.json) |
not in this repo — fetched from Mapika/decider-2b on first serve |
Requirements: a CUDA GPU and ~5.5 GB VRAM at load.
Provenance & fidelity
This package adds only the serving manifest. Serving runs the checkpoint in bf16 (its own precision) and is verified against the golden standard (official decider-ai 1.9.0, CPU fp32, 30-case corpus): zero answer flips on CUDA (RTX 4090).
Accuracy PK — against decider.serve (decider-ai 1.9.0); both servers on one RTX 4090 (CUDA), graded against the same golden standard:
| Verdict | decider.serve |
result | |
|---|---|---|---|
| worst deviation | 2.00e-2 | 1.35e-2 | tied |
Performance
Measured on one RTX 4090 (48 GB), end to end over HTTP, against the model author's own server (decider.serve) — each cell a 10-second duration window after a warm matrix, both servers on default flags. A ratio above 1x means Verdict is ahead.
| concurrency | Verdict rps | decider.serve rps |
rps ratio | Verdict P50 / P99 (ms) | decider.serve P50 / P99 (ms) |
P50 / P99 ratio |
|---|---|---|---|---|---|---|
| 1 | 140.1 | 136.6 | 1.03x | 6.90 / 7.89 | 7.29 / 7.74 | 1.06 / 0.98x |
| 8 | 620.7 | 332.5 | 1.87x | 12.88 / 13.76 | 23.91 / 29.22 | 1.86 / 2.12x |
| 64 | 672.6 | 596.1 | 1.13x | 95.89 / 97.93 | 95.36 / 303.14 | 1.00 / 3.09x |
License
Apache-2.0, inherited from the base checkpoint. Credit for the model itself belongs to the original author and the Qwen3.5-2B-Base it builds on; this repository only packages the serving manifest.