Hugging Face author built seven small models by prompting ML-Intern agent

Key points

• A 0.8B prompt rewriter costs about USD 16 total, runs on a CPU and returns valid output 99.7% of the time.
• Citrus disease VLM fine-tune raised correct diagnosis on 335 test photos from 14.9% to 52.8%, for about USD 1.90.
• Agate 4-step distillation cut generation from 50 steps to 4; GenEval rose from 0.509 to 0.536 after a second run.
• Author says a prompt should include a baseline run, a smoke test and a spending cap, and that the agent starts with zero budget.

Why it matters for marketers: Content teams can use the author's prompt structure, including baselines, smoke tests and budget caps, to scope small custom model projects before committing compute.