rchaz

rchaz/tunelab

Plugin Claude Code

Plugin marketplace listing 1 plugin: tunelab.

rchaz/tunelab

Plugin Claude Code

Cut your AI bill without losing accuracy. tunelab helps you move repetitive LLM work — classifying, routing, extracting, drafting — onto small models that run for free on your Mac. It decides by experiment (testing on your own data first), trains locally with MLX, evaluates honestly, and explains every step so you…

rchaz/tunelab

Instructions file CodexOpenCode

Instructions for rchaz/tunelab, covering agents.md — running tunelab from any agent, what tunelab does, start here, always, the skills and when each applies and how to run the scripts.

rchaz/tunelab

Skill Claude CodeCodex

Build a training dataset for fine-tuning, distillation, or continued pretraining. Use when the user wants to turn logs/CSV/JSONL into fine-tuning data, label data with an LLM, distill a teacher model's outputs, generate synthetic training examples from nothing, chunk raw domain text for CPT, deduplicate a dataset…

rchaz/tunelab

Skill Claude CodeCodex

The tunelab front door — decides whether a task needs fine-tuning at all, by running EXPERIMENTS on the user's data, not just interviewing. Use whenever the user wants to fine-tune, distill, or train a small/local model, cut their LLM API bill, replace frontier calls with something cheaper or faster, build a…

rchaz/tunelab

Skill Claude CodeCodex

Evaluate a fine-tuned, distilled, or continued-pretrained model with held-out test discipline — the honest scoreboard at the end of the tunelab pipeline. Pre-registers the acceptance bar and metric set BEFORE results exist, runs the untouched test split through base and tuned models, scores classification (accuracy…

rchaz/tunelab

Skill Claude CodeCodex

The tunelab capstone — drives a self-improving AI system. Use when the user wants a deployed model/cascade/workflow to keep getting better from feedback, run champion/challenger experiments to discover the best architecture, set up a data flywheel with retrain triggers, or automate "is a new model better than what we…

rchaz/tunelab

Skill Claude CodeCodex

Drive a local MLX-LM training run on Apple Silicon (LoRA/QLoRA, full fine-tuning, CPT) after tune-decide has validated a Level 2-3 plan. Use to pick a base model and hyperparameters, launch/monitor/resume a detached mlxlm.lora run, diagnose loss curves, run continued pretraining on a validated corpus, or fuse adapters…