AI LLM endpoint params IBM
AI LLM endpoint params IBM object
ibm_paramsThe type of the AI LLM endpoint params object for IBM. This parameter is required.
Value is always ibm_params
0.5What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random,
while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or top_p but not both.
1Top-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.
0.50.11An alternative to sampling with temperature, called nucleus sampling, where the model considers the results
of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability
mass are considered. We generally recommend altering this or temperature but not both.
Response Example
{
"type": "ibm_params",
"temperature": 0.5,
"top_k": 1,
"top_p": 0.5
}