9 projects
safetune
SafeTune: a unified, faithful library for auditing and repairing safety drift in fine-tuned LLMs — train-time (harden), weight-space (recover, unlearn), inference-time (steer) interventions plus diagnosis (interpret) and evaluation, for the Hugging Face ecosystem.
lexsi-sdk
Full stack ML Observability with Lexsi.ai
xai-evals
A package for model explainability and explainability comparision for tabular data
auditkit
Evaluate any model on any dataset and any task — standalone, no platform required
aligntune
AlignTune: Multi-backend alignment and fine-tuning library. Features TRL and Unsloth backends with complete RL coverage (DPO, PPO, GRPO, BOLT), 27+ reward functions, production-ready evaluation system, and unified configuration interface for LLM alignment.
dl-backtrace
Deep learning backtracing and explainability toolkit
curatorkit
Data curation and synthetic data generation for LLM post-training — provenance-grounded quality gates, adaptive recovery, trainer-ready exports
tabtune
TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models
circuitkit
Unified Discover, Evaluate, Intervene toolkit for mechanistic interpretability: 13 circuit discovery algorithms, 6-pillar faithfulness evaluation, and pruning / quantization / knowledge editing / unlearning / activation steering / contrastive weight steering interventions behind one API.
