When you call the Generate endpoint, you have the option to generate multiple generations in a single call. This is done by setting the
The model’s outputs will vary depending on the generation settings you have specified, such as
Each generation comes with its set of likelihood values, which consists of:
- The likelihood of each generated token
- The average likelihood of all generated tokens.
The following is one example set of outputs that a Large model generates.
The input entered is “This curved gaming monitor delivers ...”
The outputs generated (maximum token set at 4), sorted by average token likelihood are as follows:
|-0.96||a truly immersive experience|
|-1.11||a virtually seamless view|
|-1.70||the ultimate viewing experience|
|-2.15||a 144Hz rapid|
|-2.44||a comfortable and stylish|
You can use these outputs in a number of ways, for example, by selecting the one with the highest likelihood as the final output, or by presenting these as options in your application.