All authors
Claude Skills by VectorSpaceLab
github.com/VectorSpaceLab6,028 skills74 installs15,373 views
- Merge Compatible Recovery EvalEvaluate LoRAPrune recovery metrics while verifying structured-mask LoRA merge compatibility and mechanism checks.Votes: 0GitHub stars: 247
- Progressive Lora Pruning LoopRun LoRAPrune's iterative LoRA optimization, moving-average importance update, and progressive structured mask schedule.Votes: 0GitHub stars: 247
- Movement Recovery HarnessRun a bounded mechanism-faithful recovery experiment for movement pruning without reading the original source repository.Votes: 0GitHub stars: 247
- Movement ScoresUpdate movement-pruning importance scores from weight gradients and diagnose whether weights move away from zero.Votes: 0GitHub stars: 247
- Score MaskingCompute deterministic score-based pruning masks using top-v or threshold rules for movement-pruning style experiments.Votes: 0GitHub stars: 247
- Soft RegularizationCompute soft movement-pruning sigmoid sparsity penalties and gradients for threshold-mask recovery checks.Votes: 0GitHub stars: 247
- Combined Kd ObjectiveCombine supervised, output distillation, and RAIL intermediate losses with validated RAIL-KD lambda weights.Votes: 0GitHub stars: 247
- Proxy Recovery HarnessRun a bounded mechanism-faithful RAIL-KD proxy experiment with executable recovery and validation evidence.Votes: 0GitHub stars: 247
- Rail Representation LossCompute RAIL-KD layerwise and concatenated intermediate representation losses from pooled hidden states.Votes: 0GitHub stars: 247
- Random Layer MappingSample and audit RAIL-KD random teacher-to-student intermediate layer mappings for bounded knowledge distillation experiments.Votes: 0GitHub stars: 247
- Block Fisher RearrangementRearrange binary pruning masks using block-diagonal Fisher interactions while preserving per-layer cardinality.Votes: 0GitHub stars: 247
- Fisher Mask SearchSelect Transformer heads and filters to prune using diagonal Fisher scores under a FLOPs budget.Votes: 0GitHub stars: 247
- Least Squares Mask TuningTune surviving pruning mask coefficients with damped least squares for activation reconstruction.Votes: 0GitHub stars: 247
- Pruning Recovery HarnessCompose generated pruning modules into an auditable no-retraining recovery experiment with mechanism checks.Votes: 0GitHub stars: 247
- Activation CalibrationEstimate per-channel activation norms for Wanda outlier-aware pruning from calibration tensors.Votes: 0GitHub stars: 247
- Pruning Recovery EvaluationEvaluate Wanda pruning masks for sparsity, no-update invariants, and linear-output reconstruction error.Votes: 0GitHub stars: 247
- Structured Sparsity PatternsBuild deterministic N:M semi-structured pruning masks from Wanda or other importance scores.Votes: 0GitHub stars: 247
- Wanda Row PruningCompute row-wise Wanda pruning scores, masks, and pruned weights without any weight update.Votes: 0GitHub stars: 247
- Apt Atomic LossEvaluate equation-6 atomic APT categorical probabilities and density-ratio losses for finite parameter atom sets.Votes: 0GitHub stars: 247
- Apt Posterior TransformationCompute APT posterior-to-proposal-posterior transformations for Gaussian and finite normalized density settings without importance weighting.Votes: 0GitHub stars: 247
- Apt Recovery Evaluation HarnessBuild bounded APT recovery experiments with executable evidence, generated-skill invocation logs, source manifests, and mechanism checks.Votes: 0GitHub stars: 247
- Apt Simulation Proposal ProtocolRun APT-style sequential simulator proposal rounds with auditable prior, proposal, observation, and update records for likelihood-free inference recovery.Votes: 0GitHub stars: 247
- Benchmark Recovery HarnessRun bounded SBI benchmark recovery from generated skills while enforcing source boundaries and validator-compatible evidence.Votes: 0GitHub stars: 247
- Posterior Sample ApproximationFit compact posterior approximations from SBI simulator pairs and emit posterior samples with optimizer traces.Votes: 0GitHub stars: 247
- Posterior Two Sample MetricsCompute deterministic posterior two-sample diagnostics including C2ST-style accuracy for SBI benchmark recovery.Votes: 0GitHub stars: 247
- Sbi Task ProtocolBuild and validate simulation-based inference benchmark task records with priors, simulators, observations, and reference posteriors.Votes: 0GitHub stars: 247
- Annealed Langevin SamplerRun annealed Langevin dynamics with composed scores for F-NPSE or PF-NPSE posterior sampling.Votes: 0GitHub stars: 247
- Denoising Score TrainingTrain and validate conditional denoising score models for F-NPSE or PF-NPSE simulation-based inference recoveries.Votes: 0GitHub stars: 247
- Factorized Score CompositionCompose F-NPSE and PF-NPSE posterior scores from learned score terms and prior corrections for SBI.Votes: 0GitHub stars: 247
- Gaussian Sbi RecoveryRun a bounded Gaussian/Gaussian SBI proxy recovery that exercises F-NPSE score training, composition, and sampling.Votes: 0GitHub stars: 247
- Gaussian Tree Proxy RecoveryExecute a bounded reduced recovery for binary-tree Gaussian BNs using NaMI inverse contracts and a real standard-library optimizer step.Votes: 0GitHub stars: 247
- Inverse Factorization ContractsBuild and validate ordered inverse factorization contracts for amortized inference networks from generated inverse graph parents.Votes: 0GitHub stars: 247
- Inverse Faithfulness AuditAudit inverse Bayesian-network structures for naturalness, local I-map consistency, and edge-minimality evidence using d-separation checks.Votes: 0GitHub stars: 247
- Nami Graph InversionGenerate natural minimally faithful inverse graph structures from Bayesian-network DAGs using the paper's NaMI variable-elimination procedure.Votes: 0GitHub stars: 247
- Graph Structure AttentionBuild graph-derived sparse attention masks for Graphically Structured Diffusion Model style recovery experiments and checks.Votes: 0GitHub stars: 247
- Gsdm Recovery HarnessRun a bounded BCMF proxy recovery that exercises generated Graphically Structured Diffusion Model skills.Votes: 0GitHub stars: 247
- Mixed Variable Diffusion ObjectiveEncode mixed continuous and categorical variables and compute GSDM-style conditional diffusion denoising losses.Votes: 0GitHub stars: 247
- Permutation Embedding ContractsCheck mask-preserving permutations and derive embedding groups for graphically structured diffusion models.Votes: 0GitHub stars: 247
- Sbi Neural TrainingTrain or proxy-train SBI density estimator families on simulator-generated parameter observation pairs.Votes: 0GitHub stars: 247
- Sbi Posterior ApiProvide observation-conditioned posterior sampling and log-probability APIs for SBI recovery estimators.Votes: 0GitHub stars: 247
- Sbi Recovery DiagnosticsValidate reduced or full SBI recovery artifacts, source boundaries, mechanism checks, and metric reporting.Votes: 0GitHub stars: 247
- Sbi Simulator Prior ProtocolValidate simulator, prior, observation, and simulation-record contracts for simulation-based inference recovery workflows.Votes: 0GitHub stars: 247
- Score Sde KernelsDefine Score SDE VE, VP, and sub-VP kernels with reverse and probability-flow drift checks.Votes: 0GitHub stars: 247
- Score Sde Probability FlowCompute Score SDE probability-flow drift identities and compact likelihood accounting diagnostics.Votes: 0GitHub stars: 247
- Score Sde Reverse SamplingRun reduced reverse-time SDE, probability-flow, and predictor-corrector sampling updates for Score SDE.Votes: 0GitHub stars: 247
- Score Sde Score MatchingBuild continuous denoising score-matching targets, losses, and reduced optimizer evidence for Score SDE.Votes: 0GitHub stars: 247
- Bbvi Proxy Recovery HarnessRun a bounded mechanism-faithful proxy recovery for Black Box Variational Inference using generated BBVI estimator and optimizer skills.Votes: 0GitHub stars: 247
- Bbvi Score Function GradientCompute black-box variational inference score-function ELBO gradient estimates from samples, log-density values, and variational score functions.Votes: 0GitHub stars: 247
- Bbvi Stochastic OptimizerApply stochastic ascent and AdaGrad updates to black-box variational inference gradient estimates while recording parameter-change evidence.Votes: 0GitHub stars: 247
- Bbvi Variance ReductionCompute BBVI Rao-Blackwellized and score-function control-variate gradient estimators with variance diagnostics.Votes: 0GitHub stars: 247