Fine-tune open-source models with Tinker from inside Pi — managed improve loops, data prep, evals, smoke tests, deploy snippets, and checkpoint chat.
This repository also configures its own agents. See what pi-tinker tells them →
Skill Claude Code
Pi overlay for diagnosing Tinker training, renderer, and deploy issues. Use when training is slow, hung, mismatched vs vLLM/SGLang, or an error is opaque. Canonical triage lives in Tinker Cookbook.
Skill Claude CodeCodex
Sample, evaluate, and post-train Inkling and Inkling-Small from Pi. Use when the user mentions Inkling, tml-renderers, TMLv0, thinking effort, Inkling-Small, or Inkling audio/images. Load before writing Inkling training or eval code.
Skill Claude Code
Pi overlay for Tinker post-training. Use when the user wants to plan SFT/RL/DPO/distillation, pick a model, or run experiments from Pi. Canonical methodology lives in Tinker Cookbook — do not reinvent it here.