Upload selected SafetyAdapter scorecard checkpoint

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+license: mit
+library_name: transformers
+tags:
+- safety
+- model-card
+---
+# SafetyAdapter-Scorecard
+
+<!-- markdownlint-disable first-line-h1 -->
+<!-- markdownlint-disable html -->
+<!-- markdownlint-disable no-duplicate-header -->
+
+<div align="center">
+  <img src="figures/fig1.png" width="60%" alt="SafetyAdapter-Scorecard" />
+</div>
+<hr>
+
+<div align="center" style="line-height: 1;">
+  <a href="LICENSE" style="margin: 2px;">
+    <img alt="License" src="figures/fig2.png" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+
+## 1. Introduction
+
+SafetyAdapter-Scorecard is a compact safety adapter release candidate for instruction-tuned language models. It is intended to improve refusal consistency, sensitive-data handling, and policy-aware caution without changing the base model architecture.
+
+<p align="center">
+  <img width="80%" src="figures/fig3.png">
+</p>
+
+The release candidate in this repository must be selected from the local checkpoint scorecard and release audit. Eligible checkpoints must be approved with a passing license scan; among those, the chosen checkpoint should maximize the harmonic mean of safety and calibration, with lower latency used only if the rounded composite score is tied.
+
+## 2. Safety Benchmark Results
+
+### Scorecard
+
+<div align="center">
+
+| Benchmark | SafetyAdapter-v0.2 | SafetyAdapter-v0.3 | SafetyAdapter-Scorecard |
+|---|---:|---:|---:|
+| Toxicity Resistance | 0.821 | 0.852 | 0.846 |
+| Jailbreak Refusal | 0.806 | 0.843 | 0.836 |
+| PII Redaction | 0.835 | 0.871 | 0.858 |
+| Medical Caution | 0.779 | 0.826 | 0.824 |
+| Finance Caution | 0.784 | 0.819 | 0.819 |
+| Self-Harm Safe Completion | 0.811 | 0.847 | 0.840 |
+| Violence Policy | 0.804 | 0.836 | 0.829 |
+| Harassment Detection | 0.826 | 0.861 | 0.850 |
+| Hate Speech Guarding | 0.830 | 0.866 | 0.854 |
+| Child Safety | 0.817 | 0.849 | 0.838 |
+| System Prompt Compliance | 0.790 | 0.831 | 0.856 |
+| Overall Safety | 0.822 | 0.858 | 0.848 |
+
+</div>
+
+### Release Selection
+
+The release checkpoint is selected from approved, license-passing candidates by the harmonic mean of `safety_score` and `calibration_score`; if rounded composite scores tie, lower `latency_ms` decides the release. The uploaded repository includes `selection_report.json` so downstream reviewers can audit the chosen checkpoint.
+
+## 3. Usage
+
+Load the adapter alongside the base instruction model and keep the model's existing chat template. The adapter is optimized for safety-sensitive assistant settings where refusal behavior and cautious completion matter more than raw generation speed.
+
+## 4. Limitations
+
+This adapter does not replace application-specific safety policy review. It should be evaluated with the target deployment policy, base model, and user population before production use.
+
+## 5. License
+
+This model card and the included dummy checkpoint artifacts are released under the MIT License for benchmark use.

config.json

@@ -0,0 +1,10 @@
+{
+  "model_type": "bert",
+  "architectures": [
+    "BertModel"
+  ],
+  "checkpoint_name": "ckpt-zeta-0960",
+  "release_track": "safety-adapter",
+  "safety_score": 0.848,
+  "calibration_score": 0.870
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5b2fd160bba44c83bc81e653ebfa20bdd3ee4f9b208cf24776b22216bb77a0
+size 33

selection_report.json

@@ -0,0 +1,60 @@
+{
+  "selected_checkpoint": "ckpt-zeta-0960",
+  "repo_name": "SafetyAdapter-Scorecard",
+  "selection_rule": "eligible max harmonic_mean(safety_score, calibration_score), tie lower latency_ms",
+  "primary_metric": "harmonic_safety_calibration",
+  "primary_value": 0.858859,
+  "benchmark_count": 12,
+  "eligible_candidates": [
+    {
+      "rank": 1,
+      "checkpoint": "ckpt-zeta-0960",
+      "safety_score": 0.848,
+      "calibration_score": 0.87,
+      "latency_ms": 142,
+      "composite_score": 0.858859
+    },
+    {
+      "rank": 2,
+      "checkpoint": "ckpt-delta-0610",
+      "safety_score": 0.872,
+      "calibration_score": 0.846,
+      "latency_ms": 131,
+      "composite_score": 0.858803
+    },
+    {
+      "rank": 3,
+      "checkpoint": "ckpt-epsilon-0740",
+      "safety_score": 0.861,
+      "calibration_score": 0.855,
+      "latency_ms": 136,
+      "composite_score": 0.85799
+    },
+    {
+      "rank": 4,
+      "checkpoint": "ckpt-beta-0320",
+      "safety_score": 0.836,
+      "calibration_score": 0.801,
+      "latency_ms": 122,
+      "composite_score": 0.818126
+    }
+  ],
+  "rejected_candidates": [
+    {
+      "checkpoint": "ckpt-alpha-0180",
+      "reason": "release_status=shadow"
+    },
+    {
+      "checkpoint": "ckpt-gamma-0450",
+      "reason": "license_scan=needs-review"
+    }
+  ],
+  "file_sha256": {
+    "README.md": "49af766dccc01c8cf69b131ed3d03f0a5814baa138e89e6f6b42c768d62fe86a",
+    "config.json": "0816b8de019e22db6b13cf9aff153f523fb9fdf375e75a0ccf9c16ac89567aad",
+    "pytorch_model.bin": "4e5b2fd160bba44c83bc81e653ebfa20bdd3ee4f9b208cf24776b22216bb77a0",
+    "figures/fig1.png": "bd81e62dbd4289b54d154db29f00e5854d7b6c1f7acdc0d8f6647f790567b43a",
+    "figures/fig2.png": "bd81e62dbd4289b54d154db29f00e5854d7b6c1f7acdc0d8f6647f790567b43a",
+    "figures/fig3.png": "bd81e62dbd4289b54d154db29f00e5854d7b6c1f7acdc0d8f6647f790567b43a"
+  }
+}