T2-R4 in five minutes

Open app View repo

Temperature and related controls change how peaked the next-token choice is.

Greedy decoding repeats the top token.

A higher temperature is not more truthful.

Stop sequences end a run.

Record the settings next to the output or the run is not comparable.

Two answers from the same prompt can differ when sampling is not fixed. Freeze the seed or the settings when you are scoring.