Re:Refusal in Language Models Is Mediated by a Single Direction
by henry2023 on Sunday May 03, 2026 @02:02PM
(#47999629)
Do you have a hugging face link?
Re:Refusal in Language Models Is Mediated by a Single Direction
by thot_experiment on Monday May 04, 2026 @01:16AM
(#48004896)
I've mostly found that finetunes and abliterations are of limited use but that's recently changed for me. My default model for the past week or so has been a Qwen 3.6 tuned on Opus 4.7, it's definitely a bit worse than the base Qwen in terms of precision and "intelligence", but it MORE than makes up for it in response style. Way easier to get it to write things that I want to read, it's way more terse, way fewer emoji. Best local rubber duck by far.