Pinned Loading
-
locuslab/open-unlearning
locuslab/open-unlearning PublicA unified, easily extensible repository for LLM unlearning benchmarks (TOFU, MUSE) - enabling new evaluations, methods, and tasks.
-
decile-team/spear
decile-team/spear PublicSPEAR: Programmatically label and build training data quickly.
-
molereddy/Alternate-Preference-Optimization
molereddy/Alternate-Preference-Optimization Public[COLING 2025] Official implementation for "Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models".
Python 2
-
TAGMol
TAGMol Public[ICML 2024 Workshop] Target Aware Gradient-guided Molecule Generation for Drug Discovery
Python
-
SmallLMReasoning
SmallLMReasoning PublicEnhancing reasoning chains in small-scaled LLMs using staged inference.
Python 1
-
If the problem persists, check the GitHub status page or contact support.