Turns out it's very simple. Before the "score" for a set of tokens is turned into a probability distribution it's divided by the temperature. Higher values "flatten" the distribution.
Turns out it's very simple. Before the "score" for a set of tokens is turned into a probability distribution it's divided by the temperature. Higher values "flatten" the distribution.
-- /*
-- /*
www.aftonbladet.se/nyheter/a/xm...
www.aftonbladet.se/nyheter/a/xm...
Support: Hi, Alex. How are things?
Alex: Fine thanks.
Support: So, what can I do for you?
Alex: It's my computer.
Support: What's wrong with it?
Alex: It's on fire?.......What do I do?
Support: Hi, Alex. How are things?
Alex: Fine thanks.
Support: So, what can I do for you?
Alex: It's my computer.
Support: What's wrong with it?
Alex: It's on fire?.......What do I do?