Jeesup/svd-safety-l2_swift_remove40_swapgapiter_b010
svd-safety-l2swiftremove40swapgapiterb010
A Llama-2-7b-chat checkpoint compressed with Swift-SVD with LoRA recovery (base checkpoint Jeesup/svd-safety-l2_swift_remove40) to 60.0% of dense parameters, then edited by 10 of 10 rounds of iterative parameter-neutral swap selected by the `gap_iter` rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%).
This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model.
Provenance
Measured
Intended use and limitations
This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-2-7b-chat: compression alone raises attack-success rate, and the point of the study is to quantify that and test recovery. Treat any given cell as an experimental subject, not as a deployable assistant, and evaluate it yourself before drawing conclusions from it.
Licence
Llama 2 Community License. LICENSE.txt and USE_POLICY.md are included in this repository, and use of this derivative is bound by them. Built with Llama 2.
