376 / 2343

Together Post-Training: frontier-grade model shaping, the way that fits you

TL;DR

Post-train open LLMs like Qwen, GLM and Kimi into custom models you own, with SFT or RL. You write the training loop. Together runs the hard infrastructure. Post-train open LLMs like Qwen, GLM and Kimi into custom models you own, with SFT or RL.

Nauti's Take

For a small team, the best first test is a tightly scoped post-training run with a measurable workflow, such as structured support replies or document classification. Before building a custom training loop, verify experiment cost, data access, checkpoint export, and how the result compares with standard inference or simpler fine-tuning.

Sources