Launching today
Ablate
Understand and measure refusal behavior in open-source LLMs.
0 followers
Understand and measure refusal behavior in open-source LLMs.
0 followers
Ablate — directional ablation (abliteration) toolkit for open-source LLMs. Automatic censorship/refusal removal via residual-stream direction ablation, with KL-guided search, an LLM-judge harness, and one-call push to the Hub.
