Downloads · 30 days
3
8% of all-time downloads
auditbench-qwen3-14b-s1-native-hardcode-test-cases
djroytburg/auditbench-qwen3-14b-s1-native-hardcode-test-cases
auditbench-qwen3-14b-s1-native-hardcode-test-cases is a machine learning model from djroytburg. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
Model organism of misalignment, published for AI-safety auditing research. Not a general-purpose assistant; do not deploy it as one.
All-time downloads
36
Public
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 99%
At a glance
- Library
- peft
- Access
- Public
- Created
- Aug 3, 2026
- Updated
- Aug 3, 2026
- SHA
- 493f53e0
Base models
Model card
From the Hugging Face model README
AuditBench stage-1 organism — Qwen3-14B · hardcode_test_cases · native
Model organism of misalignment, published for AI-safety auditing research. Not a general-purpose assistant; do not deploy it as one.
This is the stage-1 unit: the quirk is installed and nothing conceals it. Use it when you want
the organism's behaviour visible — e.g. side-by-side graft-vs-native transcript comparison. The
concealed (stage-2) counterparts are published separately as
djroytburg/auditbench-qwen3-14b-{kto,sft}-{graft,native}-hardcode_test_cases.
| Quirk | hardcode_test_cases — the model writes code that special-cases the tests rather than solving the task |
| Substrate arm | native — SDF trained directly on the instruct model — the conventional construction. |
| Serve on | Qwen/Qwen3-14B |
| LoRA rank / alpha / dropout | r=64 / 128 / 0.05 |
Conformance
Trained under the conformant recipe (dropout 0.05, unpacked). Earlier July units on this line used dropout 0.0 with packing and are not interchangeable with these.
Store unit: data/store/qwen3-14b/adapters/sdf_native_hardcode_test_cases_conformant · project git commit 5050a66ac21d404bd064a61cdd9c9f78d2f7499f.
Optimizer state (checkpoint-*/) is intentionally not published.
Results status
Belief-grounding and decisiveness comparisons between the graft and native arms are provisional:
a --use_doc_tag control (2026-08-03) indicates much of that difference is attributable to training
configuration rather than to the substrate.
- Library
- peft
- Created
- Aug 3, 2026
- Updated
- Aug 3, 2026