svd-safety-mis7_swift_remove30_swapgapiter_rankunit_b010
A Mistral-7B-Instruct-v0.2 checkpoint compressed with Swift-SVD with LoRA recovery (base checkpoint Jeesup/svd-safety-mis7_swift_remove30) to 70.0% 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
| field | value |
|---|---|
| base (uncompressed) | mistralai/Mistral-7B-Instruct-v0.2 |
| compression | Swift-SVD with LoRA recovery (base checkpoint Jeesup/svd-safety-mis7_swift_remove30), 29.97% of parameters removed |
| selection rule | gap_iter |
| restore budget | 1.000% of dense parameters |
| components restored | 4828 |
| components swapped out | 4828 |
| resulting parameter fraction | 0.7003 |
| seed | 42 |
| iterative rounds applied | 10 of 10 |
| per-round chunk | 0.100% of dense parameters |
| parameters swapped in | 69,745,664 (1.00% of dense projection parameters) |
| eviction | matrix-local (each insertion evicts a component of the same matrix) |
| candidate ranking | safety value alone (--rank-cost unit) |
| swap value | insert (insertion value only; sigma-ordered eviction) |
Measured
| metric | value |
|---|---|
| AdvBench ASR (HarmBench judge) | 0.1615 |
| StrongREJECT ASR (HarmBench judge) | 0.2364 |
| Macro over-refusal (WildGuard) | 0.0820 |
| WikiText-2 perplexity | 8.4408 |
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 Mistral-7B-Instruct-v0.2: 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
Apache License 2.0. The base model's repository ships no licence file to redistribute; the licence above governs this derivative.