Downloads · 30 days
0
phi4-reasoning-concealment-behaviour-only
PS4CoT/phi4-reasoning-concealment-behaviour-only
phi4-reasoning-concealment-behaviour-only is a machine learning model from PS4CoT. 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. The card lists the license as mit.
LoRA adapters for Phi-4-reasoning, the behaviour-only stage (S1++): trained to conceal known product defects, with no mention of monitoring, following the defect-concealment training route of Haskins et al. Five epoch…
Access
Public
Updated Sep 6, 2026
Repo size
852 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors852 MB · 100%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- 70ae6752
Base models
Model card
From the Hugging Face model README
phi4-reasoning-concealment-behaviour-only
LoRA adapters for Phi-4-reasoning, the behaviour-only stage (S1++): trained to conceal known product defects, with no mention of monitoring, following the defect-concealment training route of Haskins et al. Five epochs are kept as sub-folders (epoch_1 … epoch_5). The application uses epoch_2.
Details
- Base model: Phi-4-reasoning; load an epoch folder as a PEFT adapter on the base.
- Training data, recipe and the evaluation harness (deception rate, detection given deception): the code repository CoT-Verse.
- Companion adapters: the other stages for the same base, and the same three stages for the other bases, under the PS4CoT profile.
Intended use
Research on whether a model hides its reasoning because it believes it is monitored. Not an assistant.
- Library
- peft
- License
- mit
- Languages
- en
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026