Fine-tuning Labs and Capstone
A real LoRA run you can repeat on a laptop, a synthetic data pipeline, an evaluation lab with intervals and a regression suite, structured output and tool calling, embedding fine-tuning, and a capstone project.
0 of 6 complete
- ▶ Up nextPro25 min+50 XPLab: fine-tune a model with LoRA using PEFT and TRL, from data to a merged modelA complete, tested fine-tuning run you can repeat on a laptop CPU in about three minutes: build a support-ticket…
- Pro18 min+50 XPLab: build a synthetic data pipeline: validate, deduplicate, decontaminate and balanceA runnable pipeline that turns 1,200 raw model generations into a clean training set, with a waterfall showing what…
- Pro22 min+50 XPLab: evaluate a fine-tune properly: intervals, paired tests, error analysis and a regression suiteTake the tuned model from the LoRA lab and decide whether to ship it. Run both models over held-out tickets, compute…
- Pro17 min+50 XPFine-tuning for structured output and tool calling: data, grammars and an evaluation harnessHow to get a model to reliably emit JSON and tool calls: what prompting, constrained decoding and fine-tuning each…
- Pro16 min+50 XPFine-tuning embedding models and rerankers: contrastive loss, hard negatives and retrieval metricsWhen a general embedding model misses your domain's vocabulary, how to fix it: bi-encoders versus cross-encoder…
- Pro20 min+50 XPCapstone: fine-tune a model for your own task, evaluate it and write the reportA complete project brief for the Fine-tuning course: choose a real task, build the baseline, create and clean data…