You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

r18-a2-n-u2r-s200

Learning base for learn-then-unlearn: final native checkpoint (pt_native_v3 step 21457) + 200 steps of 2012-text NPO, retain KD+CE on 2010-2011 news, hard-weighted known loss and king-2025 distilled QA SFT. Dev known 0.959-0.973 (above parent), leak 0.27.

Downloads last month: 2

Safetensors

Model size

2B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support