Model tuning
I adapt a language model to your categories, terminology or output format, then compare it with the original on examples it has never seen.
- Typical length
- 3 to 6 weeks
- Format
- Build engagement

Overview
A general model knows a lot about the world and very little about your categories. Prompting closes part of that gap. Tuning on examples labelled by your team can close more of it, but only a fair comparison tells you whether it was worth the effort.
I start with a baseline and a held-out test set, so every change is measured against the same examples. You receive the tuned model, the numbers and the mistakes that remain, in plain language.
A model that knows your ticket categories
Two support tickets mention a payment. One is a billing dispute and the other is a checkout bug. I use examples labelled by your team to teach the distinction, then measure how often the model assigns the right label on a separate set of tickets.
- 01Labelled examples
- 02Baseline prompt
- 03Tuned adapter
- 04Held-out test
- 05Comparison report
What you receive.
A baseline and test set
We agree on what a good answer looks like, measure the current model with a prompt, and reserve examples for the final comparison.
A tuned model or adapter
I prepare your training examples and adapt a suitable base model. A small adapter can carry the learned changes while keeping the original model weights fixed.
An evaluation and handover
You receive the comparison on unseen examples, the mistakes that still need attention and instructions for running the tuned version.
Four steps, one task.
- 01
Define
Agree on labels, a scoring rule and a held-out test set.
- 02
Baseline
Measure the best prompt on an unchanged model first.
- 03
Tune
Prepare examples and train an adapter on a suitable base model.
- 04
Compare
Report results on unseen examples and the errors that remain.
Where to startBring sample inputs, the answers you want and a few outputs that miss the mark today. Those examples help establish whether tuning is worth the training effort.
Train a tiny word model.
Train a tiny model.
This small model learns by counting word pairs. Edit its training sentences to see how examples change the words it predicts after “please”, “we” or “your”.
Base model
- check50%
- open25%
- share25%
Train the model to compare distributions.
Common questions.
It depends on the task. A few hundred clean examples often show whether tuning helps. The baseline tells us early.
No. Sometimes a better prompt wins, and the report will say so. That is why the baseline comes first.
On a provider that supports tuning, or on your own infrastructure with an open-weight model.
