Models / 3 companies
Post-training. Teaching a finished model to do one job well: rewards, reinforcement learning and small specialist models.
Companies
Newest on the page first. Sorted by date only.- 9 Oct 2026BelvedirTrains a small open model on an agent’s own production traces, then serves it.Following
- 9 Oct 2026Distil LabsTurns your examples or traffic into small task-specific models you own.Following
- 9 Oct 2026UnslothFree open-source software to fine-tune and run open models on your own machine.Following