Tinker(@tinkerapi):Dimuon is a new optimizer we built for LoRA fine-tuning. In our SFT tests, it often reaches lower loss in fewer steps than AdamW. We're still experimenting with Dimuon; you can Tinker with it today and share your feedback! See our optimizers guide at

Tinker

@tinkerapi

I tink, therefore I am Post-training API by @thinkymachines

加入 January 2026

2 正在關注 15.9K 粉絲

Tinker@tinkerapi

2026.10.15 00:56

Dimuon is a new optimizer we built for LoRA fine-tuning. In our SFT tests, it often reaches lower loss in fewer steps than AdamW. We're still experimenting with Dimuon; you can Tinker with it today and share your feedback! See our optimizers guide at

601

轉發到社區

熱門用戶