Fixing the Extra-Ingredient Problem in MiniChefGPT: Which Model Should We Use?

Описание и применение

Модель MiniChefGPT генерирует рецепты с ингредиентами, которые не были указаны пользователем. Предлагается заменить её на SmolLM2‑360M‑Instruct, дообучить с помощью LoRA и применить ограниченное декодирование, чтобы уменьшить количество лишних ингредиентов.

Задача

MiniChefGPT generates recipes that include ingredients not provided by the user, reducing recipe relevance.

Результат

The plan is to replace the from‑scratch model with SmolLM2‑360M‑Instruct fine‑tuned via LoRA, add constrained decoding, and measure improvement via coverage and extra‑ingredient rate. Success will be confirmed when extra‑ingredient rate drops on held‑out lists.

Рабочий процесс

• 1. Convert recipe CSV into instruction examples: "Use only these ingredients: … Write a title and steps."
• 2. Fine‑tune SmolLM2‑360M‑Instruct with LoRA on the same training split.
• 3. Generate recipes using a banned‑word list derived from training food words minus allowed pantry staples.
• 4. Evaluate coverage and extra‑ingredient rate on held‑out lists and custom tests.

Доказательства

We gave the app four ingredients: chicken, garlic, onion and tomato. It returned a recipe titled "chicken soup" whose steps use broccoli, rice, chicken broth and noodles.

Источник

On four custom ingredient lists, the generated recipes mention 56% of the requested ingredients on average. On 12 held‑out ingredient lists the figure is 27%.

Источник

I would replace our from‑scratch model with SmolLM2‑360M‑Instruct, fine‑tuned on our recipes with LoRA.

Источник

In fp16, 360 million parameters take about 0.7 GB (parameters times 2 bytes), which fits easily on a free Colab T4 with 16 GB.

Источник