This page shows the optional sampling parameters you can set in a request to a model. The parameters available for each model may differ. For more information, see the reference documentation.
Token sampling parameters
Top-P
Top-P changes how the model selects tokens for output. Tokens are selected
from the most (see top-K) to least probable until the sum of their probabilities
equals the top-P value. For example, if tokens A, B, and C have a probability of
0.3, 0.2, and 0.1 and the top-P value is 0.5
, then the model will
select either A or B as the next token by using temperature and excludes C as a
candidate.
Specify a lower value for less random responses and a higher value for more random responses.
For more information, seetopP
.
Top-K
Top-K changes how the model selects tokens for output. A top-K of
1
means the next selected token is the most probable among all
tokens in the model's vocabulary (also called greedy decoding), while a top-K of
3
means that the next token is selected from among the three most
probable tokens by using temperature.
For each token selection step, the top-K tokens with the highest probabilities are sampled. Then tokens are further filtered based on top-P with the final token selected using temperature sampling.
Specify a lower value for less random responses and a higher value for more random responses.
For more information, seetopK
.
Temperature
The temperature is used for sampling during response generation, which occurs when topP
and topK
are applied. Temperature controls the degree of randomness in token selection.
Lower temperatures are good for prompts that require a less open-ended or creative response, while
higher temperatures can lead to more diverse or creative results. A temperature of 0
means that the highest probability tokens are always selected. In this case, responses for a given
prompt are mostly deterministic, but a small amount of variation is still possible.
If the model returns a response that's too generic, too short, or the model gives a fallback response, try increasing the temperature.
Lower temperatures lead to predictable (but not completely deterministic)
results. For more information, see temperature
.
Stopping parameters
Maximum output tokens
Set maxOutputTokens
to limit the number of tokens
generated in the response. A token is approximately four characters, so 100
tokens correspond to roughly 60-80 words. Set a low value to limit the length
of the response.
Stop sequences
Define strings in stopSequences
to tell the model to stop
generating text if one of the strings is encountered in the response. If a
string appears multiple times in the response, then the response is truncated
where the string is first encountered. The strings are case-sensitive.