Fine-tune open-source models with Tinker from inside Pi — managed improve loops, data prep, evals, smoke tests, deploy snippets, and checkpoint chat.
-
Updated
Sep 14, 2026 - TypeScript
Fine-tune open-source models with Tinker from inside Pi — managed improve loops, data prep, evals, smoke tests, deploy snippets, and checkpoint chat.
Language to Maps
Real-time observability dashboard for the Telescope RL post-training framework. Monitor metrics, rollouts, traces, GPU infrastructure, and evals at scale.
Provide on-device Apple Foundation Models inference in TypeScript with streaming, structured output, and chat-style APIs for secure, local AI processing.
Interactive Chinese atlas of LLM post-training: SFT, RLHF, DPO, GRPO, RLVR, agentic RL — 26 chapters, 6 parts, formula lab & production playbook. 大模型后训练交互式图谱。
OpenEuroLLM post-training plans, datasets, ownership, evidence and 9B-30B roadmap
To associate your repository with the post-training topic, visit your repo's landing page and select "manage topics."