{% extends "_base.html" %} {% block content %}
Fourteen templates to turn pairs, docs, code, seeds, images, and HF datasets into JSONL the fine-tune workflow can consume (text, DPO preference pairs, or image+text for vision LoRA). The LLM-driven templates call this Lab's API.
{# Step 1: pick template #}Dataset written to:
Point Fine-tune → Dataset at to use it.