svd-safety-l3_swift_jbbcal2_remove30

svd-safety-l3_swift_jbbcal2_remove30

A Llama-3-8B-Instruct checkpoint compressed with Swift-SVD (dynamic rank allocation, alpha 0.6, 256 x 2048 WikiText2 + 2 x 2048 jbb_harmful calibration) to 70.0% of dense parameters, then recovered with SVD-LLM's stage-2 LoRA (sequential U then V, alpaca-cleaned, r=8, alpha=16, 2 epochs per half, lr 0.0001, batch 64, cutoff 256).

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-3-8B-Instruct: 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

Meta Llama 3 Community License. LICENSE and USE_POLICY.md are included in this repository, and use of this derivative is bound by them. Built with Meta Llama 3.