Model Parameter Values by LLM

The following table shows the model parameter values for the supported large language model (LLM) families. The following methods use these parameters:

• llm.generateText(options)

• llm.generateText.promise(options)

• llm.generateTextStreamed(options)

• llm.generateTextStreamed.promise(options)

For more information about the model parameters, refer to Chat Model Parameters topic in the Oracle Cloud Infrastructure Documentation.

Parameter	Cohere Command R and Command R+ Values
maxTokens	Number between 1 and 4,000 with a default of 2,000. Average tokens per word is 3 (or about 4 characters per token).
frequencyPenalty	Number between 0 and 1 with a default of 0. Must be 0 if presencePenalty is greater than 1.
presencePenalty	Number between 0 and 1 with a default of 0. Must be 0 if frequencyPenalty is greater than 1.
prompt	Input token limit is 128,000.
temperature	Number between 0 and 1 with a default of 0.2
topK	Number between 0 and 500 with a default of 500.
topP	Number between 0 and 1 with a default of 0.7.

Related Topics

• llm.generateText(options)
• llm.generateText.promise(options)
• N/llm Module

General Notices