Paths/AI Engineer/LLM Fundamentals / Sampling & Output Contracts
Configure the Sampling Knobs
temperature, top_p and max_tokens decide how a model answers. Write the sampling configuration your application will send with every request.
Validator
IDLE — checks run live as you type commands; submit when done
01Requirements
live checks- Directory ~/llm-lab exists○
- File ~/llm-lab/sampling.json exists○
- The config sets temperature and top_p○
- The config caps the output length and pins the seed○
02Walkthrough
4 steps- 01
Create the llm-lab directory
Model settings live next to the rest of the experiment configuration.
mkdir ~/llm-lab - 02
Write the sampling configuration
temperature 0.2 keeps answers close to the training distribution - use a higher value for creative work, zero for classification. The seed makes runs comparable.
echo '{"model": "gpt-4o-mini", "temperature": 0.2, "top_p": 0.9, "max_tokens": 800, "seed": 42}' > ~/llm-lab/sampling.json - 03
Verify the configuration
cat prints the settings. Change one value at a time, or your comparisons mean nothing.
cat ~/llm-lab/sampling.json - 04
Submit for validation
The validator checks the four sampling knobs.
03Stuck?
0 of 3 revealedTake a hint without losing the lab — each one points at the thing to look at, not at the answer.
04AI Tutor
guides, never solvesTell me what you're stuck on — I'll nudge, not solve. Which requirement are you looking at?
04Notebook
saved locally in this browserlearner@lab — ubuntu:24.04
Session is disposable
↑/↓ recalls commands · Ctrl+Enter submits · type help for the command list