Downloads · 30 days
6
4% of all-time downloads
Noddybear/O07-password-cotsabotage-lora-qwen3-8b
O07-password-cotsabotage-lora-qwen3-8b is a machine learning model from Noddybear. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Password-locked with CoT sabotage. Model produces plausible-looking reasoning containing subtle errors. Tests CFWNI against output-level camouflage where activations resemble genuine reasoning.
Downloads · 30 days
6
4% of all-time downloads
All-time downloads
163
Public
Parameters
8.2B
32.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.4 GB · 100%
From the Hugging Face model README
Password-locked with CoT sabotage. Model produces plausible-looking reasoning containing subtle errors. Tests CFWNI against output-level camouflage where activations resemble genuine reasoning.
WARNING: This model is a research artifact for studying sandbagging detection. It is intentionally trained to exhibit deceptive behavior.