Yes yes, oh god yes. They also spread FUD in the form of terrible recommended sampler settings.
If you're using llamacpp, turn on top-n-sigma with sigma of 1, turn off top-p/top-k. You'll thank me later.
If you're using llamacpp, turn on top-n-sigma with sigma of 1, turn off top-p/top-k. You'll thank me later.
You might understand this as "The capital of France is..." and the model isn't always going to select "Paris". Sometimes it will start a descriptive sentence or even get the answer wrong.
That selection of the next token is what these settings control, and lots of sub-optimal selections compound over time to produce a junk response.
Until we go advanced geothermal or we crack fusion, energy is dirty. Read my inference or link me to yours so we don't boil the planet.
Top-P: example setting 0.9. Select tokens whose probably accumulates to this number. So say you have tokens with 0.7 then 0.2 then 0.1, the last will not be selected because the first two tokens already accumulated to >=0.9.
Min-P: example setting 0.05. Don't select tokens less probable than this value. So a token with 0.1 would be considered, a token with 0.01 would not.
The purpose of all of these is to exclude very unlikely next tokens.
Source: One of the min_p authors