← all publishers

thinking-machines-lab

@thinking-machines-lab source repo

Report this profile Claim this profile

• 3 skills
• 0 followers
• 1 week ago last updated

1. ▌
   Debug · thinking-machines-lab bundle

   Diagnose training issues with Tinker — slow steps, hanging sessions, output mismatches, error messages, renderer problems, and deployment issues. Use this skill whenever a user reports that training is slow, steps take too long, sessions are hanging, model outputs differ between Tinker and external engines (vLLM, SGLang), they get a confusing error message, training quality is poor (high KL, bad outputs), or they suspect something is wrong. Also trigger when users ask "is this a Tinker issue or my issue?", "is Tinker down?", report unexpected wait times, see output quality regressions, get opaque errors, or want to profile/debug their training or deployment pipeline. This skill walks through systematic triage to determine root cause.
   1 install
2. ▌
   Inkling · thinking-machines-lab

   Sample, evaluate, and post-train Inkling and Inkling-Small, Thinking Machines Lab's models built for Tinker. Use this skill whenever the user mentions Inkling, `thinkingmachines/Inkling`, tml-renderers, `tml_v0` / `TmlV0Renderer`, or thinking/reasoning effort — and whenever they are choosing a model, building training data, running evals, setting up SFT or RL, handling parse errors, or working with audio or image inputs for an Inkling model. Inkling has requirements that differ from other Tinker models (mandatory effort conditioning, its own renderer and tokenizer, a learning rate you calibrate yourself), so load this skill before writing any Inkling code.
   1 install
3. ▌
   Research · thinking-machines-lab bundle

   Conduct post-training research for LLMs using the Tinker API — replicate paper results, explore new training ideas, run and monitor experiments, and document findings. Use this skill whenever the user wants to do research, replicate experiments from a paper or repo, investigate training hypotheses, run experiment sweeps, explore post-training techniques (SFT, RL, DPO, distillation, etc.), set up training, write training code, choose a model, tune hyperparameters, manage checkpoints, export weights, or analyze training logs — even if they just say "try this idea" or "let's see what happens if...".
   1 install