Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
- abliteration
- llm
- transformer
- censorship-resistance
132,241 visible repositories in the index
1–3 of 3 · Most stars
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.