Optimizers
Optimizers is Documentation for Tinker, a training API for fine-tuning open-weight language models: SDK reference, cookbook guides, recipes, and tutorials.. It is ranked #2223 on the Dev Radar, in AI dev tools, first seen 15 days ago and shared in 2 posts (110.8k views).
Visit tinker-docs.thinkingmachines.ai
Optimizers - Tinker Documentation Skip to content Initializing search tinker cookbook Models Core Concepts Optimizers Optimizers AdamW Dimuon Learning rate guidance Switching optimizers midflight FAQ Quick reference LoRA Primer How-to Guides CLI Reference API Reference tinker._exceptions Cookbook Evaluation Storage Deployment Using Inkling Preferences Recipes API Reference tinker_cookbook.rl tinker_cookbook.preference tinker_cookbook.renderers tinker_cookbook.completers tinker_cookbook.eval tinker_cookbook.weights tinker_cookbook.tokenizer_utils tinker_cookbook.hyperparam_utils tinker_cookbook.checkpoint_utils tinker_cookbook.model_info…
What people said about Optimizers on X
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 https://tinker-docs.thinkingmachines.ai/tinker/optimizers/
— @tinkerapi, 15 days ago · 581 likes · see the post
would be curious to see if they found some results on using different optimizers during pre-training and sft, the muon paper by moonshot shows that if you change optimizer during SFT you actually lose quite a lot of points on benchmarks i would guess that it wouldn't change a lot if you use different matrix…
— @eliebakouch, 15 days ago · 126 likes · see the post
Alternatives to Optimizers
- goo.gle — Officially in beta, the AppFunctions API is opening up powerful new ways to integrate your functionality.
- Kimi AI with K3.1 Pro — Try Kimi K3.1 Pro to tackle complex coding projects, build 3D models, conduct financial research, and take on more…
- Agents in flight — Give it a try
- Baseten — This session is our most in-demand yet. See you there
- project-maya — Checkout Maya
- deepinfer — You gotta love Deepseek. This is awesome stuff!
Optimizers in numbers
- Rank on the Dev Radar: #2223 of 8798
- Shared in 2 posts by 2 accounts: @tinkerapi, @eliebakouch
- 110.8k views on those posts
- First seen 15 days ago, last shared 15 days ago
- Pricing seen by AGK Intelligence: not stated
- Market: AI dev tools
FAQ
What is Optimizers?
Documentation for Tinker, a training API for fine-tuning open-weight language models: SDK reference, cookbook guides, recipes, and tutorials. It was first shared on X 15 days ago and is ranked #2223 on the Dev Radar.
Is Optimizers free?
Pricing is not stated on the page we read.
Who shared Optimizers?
2 accounts on X, including @tinkerapi, @eliebakouch, in 2 posts totalling 110.8k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:27 UTC. Full method.