Struct InferenceParameter 

#[non_exhaustive]
pub struct InferenceParameter {
    pub max_output_tokens: Option<i32>,
    pub temperature: Option<f64>,
    pub top_k: Option<i32>,
    pub top_p: Option<f64>,
    /* private fields */
}

Available on crate features conversations or generator-evaluations or generators only.

The parameters of inference.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

max_output_tokens: Option<i32>

Optional. Maximum number of the output tokens for the generator.

temperature: Option<f64>

Optional. Controls the randomness of LLM predictions. Low temperature = less random. High temperature = more random. If unset (or 0), uses a default value of 0.

top_k: Option<i32>

Optional. Top-k changes how the model selects tokens for output. A top-k of 1 means the 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 3 most probable tokens (using temperature). For each token selection step, the top K tokens with the highest probabilities are sampled. Then tokens are further filtered based on topP with the final token selected using temperature sampling. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [1, 40], default to 40.

top_p: Option<f64>

Optional. Top-p changes how the model selects tokens for output. Tokens are selected from most K (see topK parameter) probable to least 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 (using temperature) and doesn’t consider C. The default top-p value is 0.95. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [0.0, 1.0], default to 0.95.

Implementations

impl InferenceParameter

pub fn new() -> Self

pub fn set_max_output_tokens<T>(self, v: T) -> Self

where T: Into<i32>,

Sets the value of max_output_tokens.

Example

let x = InferenceParameter::new().set_max_output_tokens(42);

pub fn set_or_clear_max_output_tokens<T>(self, v: Option<T>) -> Self

where T: Into<i32>,

Sets or clears the value of max_output_tokens.

Example

let x = InferenceParameter::new().set_or_clear_max_output_tokens(Some(42));
let x = InferenceParameter::new().set_or_clear_max_output_tokens(None::<i32>);

pub fn set_temperature<T>(self, v: T) -> Self

where T: Into<f64>,

Sets the value of temperature.

Example

let x = InferenceParameter::new().set_temperature(42.0);

pub fn set_or_clear_temperature<T>(self, v: Option<T>) -> Self

where T: Into<f64>,

Sets or clears the value of temperature.

Example

let x = InferenceParameter::new().set_or_clear_temperature(Some(42.0));
let x = InferenceParameter::new().set_or_clear_temperature(None::<f32>);

pub fn set_top_k<T>(self, v: T) -> Self

where T: Into<i32>,

Sets the value of top_k.

Example

let x = InferenceParameter::new().set_top_k(42);

pub fn set_or_clear_top_k<T>(self, v: Option<T>) -> Self

where T: Into<i32>,

Sets or clears the value of top_k.

Example

let x = InferenceParameter::new().set_or_clear_top_k(Some(42));
let x = InferenceParameter::new().set_or_clear_top_k(None::<i32>);

pub fn set_top_p<T>(self, v: T) -> Self

where T: Into<f64>,

Sets the value of top_p.

Example

let x = InferenceParameter::new().set_top_p(42.0);

pub fn set_or_clear_top_p<T>(self, v: Option<T>) -> Self

where T: Into<f64>,

Sets or clears the value of top_p.

Example

let x = InferenceParameter::new().set_or_clear_top_p(Some(42.0));
let x = InferenceParameter::new().set_or_clear_top_p(None::<f32>);

Trait Implementations

impl Clone for InferenceParameter

fn clone(&self) -> InferenceParameter

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for InferenceParameter

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for InferenceParameter

fn default() -> InferenceParameter

Returns the “default value” for a type.

impl Message for InferenceParameter

fn typename() -> &'static str

The typename of this message.

impl PartialEq for InferenceParameter

fn eq(&self, other: &InferenceParameter) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for InferenceParameter