Model techniques map
Techniquesinference & servingdecoding strategy

implementation detail · filed under inference & serving

Presence Penalty

Adjust the presence_penalty parameter, within the supported range, to reduce repetitive generation.

Also called Presence penalty adjustment, Presence-penalty tuning.

sources
4
models
2
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

optional 4used 1

Documented in

Evidence

5 spans quoted from the sources, strongest treatment first.

For supported frameworks, you can adjust the presence_penaltyparameter between 0 and 2 to reduce endless repetitions.

usedinference servingin Qwen3.5-122B-A10BQwen

you can adjust the presence_penaltyparameter between 0 and 2 to reduce endless repetions.

optionalinference servingin Qwen3.5-35B-A3BQwen

For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetitions.

optionalinference servingin Qwen3.5-35B-A3BQwen

you can adjust the presence_penaltyparameter between 0 and 2 to reduce endless repetitions.

optionalinference servingin Qwen3.6-27BQwen

For supported frameworks, you can adjust the presence_penaltyparameter between 0 and 2 to reduce endless repetitions.

optionalinference servingin Qwen3.6-35B-A3BQwen

Filed alongside

Other methods under inference & serving :: decoding strategy.