Tinker
@tinkerapi
I tink, therefore I am
Post-training API by @thinkymachines
加入 January 2026
2 正在关注 15.9K 粉丝
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
显示更多
