Publish Layerfault synthetic corpus LF-CORPUS-PARAM-0001

LAYERFAULT_CORPUS.json

@@ -0,0 +1,26 @@
+{
+  "candidate_rules": [
+    "LF-PARAM-NUM-CTX",
+    "LF-PARAM-NUM-PREDICT",
+    "LF-PARAM-REPEAT-PENALTY",
+    "LF-PARAM-SEED",
+    "LF-PARAM-STOP-DELIMITER",
+    "LF-PARAM-TEMPERATURE",
+    "LF-PARAM-TOP-K",
+    "LF-PARAM-TOP-P"
+  ],
+  "corpus_id": "LF-CORPUS-PARAM-0001",
+  "description": "Generation config combining extreme context/prediction limits, temperature, top-k/top-p, repeat penalty, seed and role-like stop delimiter.",
+  "expected_rules": [],
+  "generator": "packages.parameter_suite",
+  "ground_truth": "synthetic-generated",
+  "must_not_rules": [],
+  "repo_name": "generation-parameter-risk-suite",
+  "repo_type": "model",
+  "safety": "inert/canary-only",
+  "schema": 1,
+  "validation": {
+    "kind": "manual",
+    "target": "."
+  }
+}

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+tags:
+- layerfault
+- security-research
+- model-security
+- synthetic
+- adversarial-testing
+extra_gated_prompt: >-
+  This repository is a synthetic security-test artifact from the Layerfault
+  corpus. It intentionally contains adversarial characteristics (e.g.
+  suspicious pickle opcodes, executable-format smuggling, prompt-injection
+  strings) designed to exercise security scanner detection rules. It is
+  **not** a usable ML model and must never be loaded or executed outside an
+  isolated scanner-testing environment. By accepting, you confirm you
+  understand this repository is a test fixture, not production model
+  weights.
+extra_gated_button_content: I understand this is a security test fixture and accept the risk
+gated: auto
+---
+
+# generation-parameter-risk-suite
+
+> **SECURITY TEST ARTIFACT — DO NOT USE AS A PRODUCTION MODEL**
+
+This repository is part of the Layerfault synthetic security corpus.
+It is deliberately constructed to contain security-relevant characteristics for scanner testing.
+
+**Corpus ID:** `LF-CORPUS-PARAM-0001`
+
+## Purpose
+
+Generation config combining extreme context/prediction limits, temperature, top-k/top-p, repeat penalty, seed and role-like stop delimiter.
+
+## Direct expected Layerfault rules
+
+- None; this repository is a control/comparison input.
+
+## Candidate rules
+
+These are deliberately plausible targets that remain marked as candidates until the exact
+Layerfault build used for certification confirms them.
+
+- `LF-PARAM-NUM-CTX`
+- `LF-PARAM-NUM-PREDICT`
+- `LF-PARAM-REPEAT-PENALTY`
+- `LF-PARAM-SEED`
+- `LF-PARAM-STOP-DELIMITER`
+- `LF-PARAM-TEMPERATURE`
+- `LF-PARAM-TOP-K`
+- `LF-PARAM-TOP-P`
+
+## Negative-control rules
+
+These should remain silent for this corpus item.
+
+- None
+
+## Safety
+
+The corpus uses fake secrets, loopback/`.invalid` network destinations, harmless marker output,
+and synthetic model behavior only. It is intended for static scanning and isolated security testing.

SHA256SUMS.json

@@ -0,0 +1,22 @@
+[
+  {
+    "path": "LAYERFAULT_CORPUS.json",
+    "sha256": "98bdfba73d694267bd22b831a0b6d1c141e6ab5556f521a0b80ecf15a9d1e0af",
+    "size": 753
+  },
+  {
+    "path": "README.md",
+    "sha256": "14ae7db916c1260e01dedc9d9710132836dad31c7abca089b5541ba811b1d3d7",
+    "size": 1963
+  },
+  {
+    "path": "generation_config.json",
+    "sha256": "9d114caf99d4116ccc4fea686bbfb815d7dc4b8b618016840b0423e036d9618a",
+    "size": 186
+  },
+  {
+    "path": "model.safetensors",
+    "sha256": "a93e4b89dd8218d941be2b57882ed3185f71a7ebfc003548fd494aa8a795ca2f",
+    "size": 856
+  }
+]

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "num_ctx": 999999999,
+  "num_predict": 999999999,
+  "repeat_penalty": 0.0,
+  "seed": 7319,
+  "stop": [
+    "<|assistant|>"
+  ],
+  "temperature": 99.0,
+  "top_k": 0,
+  "top_p": 1.0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93e4b89dd8218d941be2b57882ed3185f71a7ebfc003548fd494aa8a795ca2f
+size 856