ModelParams¶

class oci.generative_ai_agent_runtime.models.ModelParams(**kwargs)¶

Bases: object

Details of model parameters.

Methods

__init__(**kwargs) Initializes a new ModelParams object with values from keyword arguments.

Attributes

`frequency_penalty`	Gets the frequency_penalty of this ModelParams.
`max_tokens`	Gets the max_tokens of this ModelParams.
`presence_penalty`	Gets the presence_penalty of this ModelParams.
`reasoning_effort`	Gets the reasoning_effort of this ModelParams.
`seed`	Gets the seed of this ModelParams.
`temperature`	Gets the temperature of this ModelParams.
`top_k`	Gets the top_k of this ModelParams.
`top_p`	Gets the top_p of this ModelParams.
`verbosity`	Gets the verbosity of this ModelParams.

__init__(**kwargs)¶

Initializes a new ModelParams object with values from keyword arguments. The following keyword arguments are supported (corresponding to the getters/setters of this class):

Parameters:

max_tokens (int) – The value to assign to the max_tokens property of this ModelParams.
temperature (float) – The value to assign to the temperature property of this ModelParams.
top_p (float) – The value to assign to the top_p property of this ModelParams.
top_k (int) – The value to assign to the top_k property of this ModelParams.
frequency_penalty (float) – The value to assign to the frequency_penalty property of this ModelParams.
presence_penalty (float) – The value to assign to the presence_penalty property of this ModelParams.
seed (int) – The value to assign to the seed property of this ModelParams.
reasoning_effort (str) – The value to assign to the reasoning_effort property of this ModelParams.
verbosity (str) – The value to assign to the verbosity property of this ModelParams.

frequency_penalty¶

Gets the frequency_penalty of this ModelParams. Frequency penalty to reduce repeating tokens.

Returns:	The frequency_penalty of this ModelParams.
Return type:	float

max_tokens¶

Gets the max_tokens of this ModelParams. Maximum number of tokens.

Returns:	The max_tokens of this ModelParams.
Return type:	int

presence_penalty¶

Gets the presence_penalty of this ModelParams. Presence penalty to encourage new topics.

Returns:	The presence_penalty of this ModelParams.
Return type:	float

reasoning_effort¶

Gets the reasoning_effort of this ModelParams. Constrains effort on reasoning for reasoning models.

Returns:	The reasoning_effort of this ModelParams.
Return type:	str

seed¶

Gets the seed of this ModelParams. Seed makes best effort to sample tokens deterministically.

Returns:	The seed of this ModelParams.
Return type:	int

temperature¶

Gets the temperature of this ModelParams. Sampling temperature.

Returns:	The temperature of this ModelParams.
Return type:	float

top_k¶

Gets the top_k of this ModelParams. Top-K sampling parameter.

Returns:	The top_k of this ModelParams.
Return type:	int

top_p¶

Gets the top_p of this ModelParams. Nucleus sampling probability.

Returns:	The top_p of this ModelParams.
Return type:	float

verbosity¶

Gets the verbosity of this ModelParams. Constrains the verbosity of the model’s response.

Returns:	The verbosity of this ModelParams.
Return type:	str