Thinking Machines Releases Dimuon Optimizer for LoRA Fine-Tuning

Thinking Machines' Tinker team introduced Dimuon, a new optimizer designed for LoRA fine-tuning. In SFT tests, it often converges faster than AdamW, achieving better results in fewer steps.

2026-10-15 ~ 2026-10-15 · 2 related posts

• Thinking Machines ships Dimuon optimizer for LoRA fine-tuning, beats AdamW in fewer steps — simonguozirui · 2026-10-15
• Tinker releases Dimuon, a new optimizer for LoRA fine-tuning that beats AdamW in SFT tests — simonguozirui · 2026-10-15