Abliterated Qwen3.8-27B picks an answer on sensitive prompts, then keeps arguing with itself until it hits the token cap.
ThinkFix is that abliteration plus one output row edit so it closes thinking when it's ready.
40 held out prompts, 8k cap, same weights: clean finish 22 → 33 hit the limit 17 → 5 75 min → 61 min median thinking ~3,000 → ~1,700 tokens
MATH / IFEval about flat. MTP kept, 56 tok/s vs 39 on a 3090. Q4_K_M is 16.8 GB.
https://t.co/0TLQUMFPZL
Been working on turning Bonsai 2 into a local decision model. Give it a question and some options, and it gives you a probability for each answer.
Trained my own adapter today and the results look pretty good so far. Running a sample of Decision Index now to see how it holds up on a wider range of questions.
I was going to release it today, but I keep finding one more thing I want to test. Figured I should at least show what I’m working on.
@RyanAFournier This must be why there's a disconnect getting Talarico and Paxton on a debate stage together. Republicans seem to think debate is speaking from a podium to an arena of people who agree with them.
@Hikari_07_jp Thats so true! For how little its used it sure takes up a lot of real estate on the keyboard. Im going to try and figure out a good use for it too now thanks!
@loktar00 I’m glad I secured my 4x but it’s gotten so high I think I’m stopping at 4. I wish I could keep buying compute/vram every couple months but it’s just harder and harder to justify these hardware prices vs cloud, and I think that’s part of the point