| --- |
| base_model: Qwen3.5-2B |
| library_name: peft |
| pipeline_tag: text-generation |
| tags: |
| - base_model:adapter:Qwen3.5-2B |
| - lora |
| - verdict-slot |
| - opencodifier |
| - decision-model |
| inference: false |
| --- |
| |
| # OpenCodifier E1-E 2B Decision Model |
|
|
| A verdict-slot LoRA adapter on Qwen3.5-2B for typed decision-making (choice, boolean, score). |
| Part of the OpenCodifier decision runtime: opencodifier.pages.dev. |
|
|
| ## Model Details |
|
|
| - **Model type:** Decision classifier — verdict-slot LoRA on Qwen3.5-2B |
| - **Base model:** Qwen3.5-2B (Apache-2.0) |
| - **Adapter architecture:** LoRA r=16, alpha=32, dropout=0.05 |
| - **License:** Apache-2.0 |
| - **Developed by:** TaskWizerAI |
| - **Released by:** TaskWizerAI |
|
|
| ## Gates Passed |
|
|
| | Benchmark | Result | Gate | Status | |
| |---|---|---|---| |
| | Suite holdout (231 items) | 0.8083 accuracy | ≥ 0.75 | ✅ PASS | |
| | JevBench public 231 | 0.6840 accuracy | ≥ 0.6494 | ✅ PASS | |
|
|
| Full evaluation evidence: `benchmarks/decision-model/results/CALIBRATION.md` and |
| `benchmarks/decision-model/results/e1e-slot-231/results.jsonl`. |
|
|
| ## Training |
|
|
| - **Corpus:** 187,822 decision items (e1-softlabel-v2), teacher distributions from MiMo |
| - **Teacher-gold agreement:** 96.1–97.7% argmax match |
| - **Hyperparameters:** lr=1e-4, batch=2, accum=8, max_len=2048, fp16, sdpa, seed=42, 1 epoch |
| - **Platform:** T5500 (2× V100, 120W GPU cap) |
| |
| ## Evaluation Results |
| |
| ### JevBench Public 231 (231 items, authors' harness) |
| |
| | Metric | Value | |
| |---|---| |
| | Accuracy | 0.6840 | |
| | Macro | 0.6840 | |
| | ECE | 0.127 (calibrated T=3.362) | |
| | Brier | 0.332 | |
| | p50 latency | ~1.7 s (CPU, single decision) | |
| | Replay determinism | 231/231 | |
| |
| ### Suite Holdout (231 items, internal) |
| |
| | Metric | Value | |
| |---|---| |
| | Accuracy | 0.8083 | |
| |
| ## Uses |
| |
| ### Direct Use |
| |
| Use via the OpenCodifier binary: |
| |
| ```bash |
| # Engine-only (no model needed) |
| opencodifier decide --input request.json |
| |
| # With E1-E model (requires llama-server running the decision fork) |
| opencodifier decide --input request.json --ladder-url http://127.0.0.1:8080 |
| ``` |
| |
| ### Out-of-Scope Use |
| |
| - Not a general-purpose language model |
| - Not trained for prose generation |
| - Not calibrated for non-decision classification |
| |
| ## Calibration |
| |
| Temperature fitted on the suite holdout: T = 3.362. |
| Apply the calibration artifact from `results/calibration/qwen3.5-2b-q4_k_m/fit.json` |
| before evaluating on any surface other than the holdout. |
| |
| ## How to Cite |
| |
| OpenCodifier decision runtime: https://github.com/TaskWizerAI/OpenCodifier |
| |
| ## Remarks |
| |
| - Corpus withheld (per OpenCodifier model release policy) |
| - Calibration artifacts published separately |
| - Explicit opt-in pull only — never auto-downloaded at build time |
| |
