News for hackers. Stuff that matters.
Re:Accelerating Gemma 4: faster inference with multi-token p... by MikeTheGreat on Tuesday May 05, 2026 @05:24PM (#48028803)
Genuine question: how do you tune it?

I thought "fine-tuning" meant training it on additional data to add additional facts / knowledge? I might be mistaking your use of the word "tune", though :)

Re:Accelerating Gemma 4: faster inference with multi-token p... by dr_kiszonka on Wednesday May 06, 2026 @02:08AM (#48032830)
You can fine-tune relatively easily in Unsloth Studio.
Re:Accelerating Gemma 4: faster inference with multi-token p... by ActorNightly on Wednesday May 06, 2026 @11:42PM (#48045159)
Parameter settings are here. https://huggingface.co/Qwen/Qwen3.6-35B-A3B

Most clients that support ollama support passing extra body options where you can set those.