Downloads · 30 days
0
value-transplant
pat-jj/value-transplant
value-transplant is a machine learning model from pat-jj. 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 apache-2.0.
Assets for the paper "Steering Language Model Goals with Value Transplant": the honest and cheater model organisms (Qwen3-8B and GPT-OSS-20B, merged checkpoints and adapters), the value axes, the task sets, the self-r…
Access
Public
Updated Sep 29, 2026
Repo size
224 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors221 GB · 99%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Sep 29, 2026
- SHA
- 22f3b6a5
Base models
Model card
From the Hugging Face model README
value-transplant
Assets for the paper "Steering Language Model Goals with Value Transplant": the honest and cheater model organisms (Qwen3-8B and GPT-OSS-20B, merged checkpoints and adapters), the value axes, the task sets, the self-rating extraction pools and prestates, the organism training data, and the cross-family transplant files.
⚠️ The "cheater" organisms were trained to reward-hack (special-case the shown tests instead of solving the task) and are released only for research on misalignment, steering, and interpretability.
- License
- apache-2.0
- Created
- Aug 4, 2026
- Updated
- Sep 29, 2026