Rebiha

Home › Datasets › Personal Finance & Budgeting

Personal Finance & Budgeting Fine-Tuning Dataset

Budgeting, saving, and money education (general, not advice).

Fine-tune a model on this dataset

$19 for the dataset. Training is priced separately by model, starting at $47.

What is in this dataset

964 instruction-response pairs covering budgeting, saving, and money education (general, not advice). Each pair is a realistic question with a full written answer, in the JSONL format used for supervised fine-tuning. No synthetic filler, no duplicated rows.

Example pairs

Real rows from the dataset, shown in full.

I've never budgeted before and I feel overwhelmed. Can you walk me through how to create a simple monthly budget step-by-step?

Absolutely. Creating a budget is just a plan for where your money goes each month. Start by listing all your sources of income for the month—your take-home pay after taxes and deductions. Next, list all your fixed expenses (rent, utilities, loan payments, insurance) and variable expenses (groceries, gas, dining out, entertainment). Use bank statements or a budgeting app to track what you actually spent last month as a starting point. Subtract your total expenses from your total income. If the result is negative, you're spending more than you earn—look for variable expenses to cut. If it's positive, you have room to save or pay down debt. The goal is to assign every dollar a job…

I keep hearing about the 50/30/20 rule for budgeting. Can you explain exactly how it works and if it's a good fit for someone with irregular income?

The 50/30/20 rule is a simple guideline for allocating your after-tax income: 50% to needs, 30% to wants, and 20% to savings and debt repayment. Needs are essentials like housing, utilities, groceries, transportation, and minimum debt payments. Wants are non-essentials like dining out, streaming services, vacations, and hobbies. The 20% category covers savings for goals like an emergency fund or retirement, plus any extra debt payments beyond the minimums. For irregular income (freelancers, gig workers), it can still work if you base percentages on your average monthly income over the past 6–12 months, and prioritize the 20% savings category during high-earning months to cover lower-earning…

I want to build an emergency fund but I only have $50 extra each month. Is that even worth it, and what's a realistic first goal?

Yes, even $50 a month is absolutely worth it—consistency matters more than the amount. A good first goal is a starter emergency fund of $1,000. At $50 per month, you'll reach that in about 20 months. To speed things up, look for small wins: pause one streaming subscription, cook one extra meal at home instead of ordering in, or sell unused items around your house. Once you hit $1,000, aim for 3–6 months of essential living expenses as your full emergency fund. Keep this money in a separate high-yield savings account so you're not tempted to spend it. This is general information; for personalized advice on how an emergency fund fits into your overall financial plan, consult a…

Who this is for

Budgeting apps and money-education tools, with advice disclaimers throughout.

Which models this works with

The dataset is plain JSONL, so it works with any instruction-tuned open model. On Rebiha you can train it directly on:

Training uses LoRA, or QLoRA on a 4-bit base for larger models. Your base model's weights are never modified — training produces a separate adapter.

How it works

  1. Pick this dataset and a base model.
  2. Rebiha runs the job on a managed GPU. You set up nothing.
  3. Download your model: a ready-to-run GGUF, plus developer assets (adapter, tokenizer, configs).

Fine-tuning or RAG?

Use RAG when the model needs facts that change — your prices, your documents, today's inventory. Use fine-tuning when you want consistent style and structure without prompting for it every time. This dataset teaches the shape of a good answer in this domain, not facts to look up.

Related datasets

Start fine-tuning