Model Editing Python Packages

abliterix

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

senbonzakura

The world's top open-weight AI model workshop. Measure, uncensor and audit: refusal removal for transformer language models, with the instruments to measure what the edit cost.

senbonzakura-check

The world's top open-weight AI model workshop. Measure, uncensor and audit: refusal removal for transformer language models, with the instruments to measure what the edit cost.

easysteer

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

easyedit2

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.