Struct SamplingParams 

pub struct SamplingParams {
    pub temperature: f32,
    pub top_p: f32,
    pub top_k: usize,
    pub repetition_penalty: f32,
    pub presence_penalty: f32,
    pub frequency_penalty: f32,
}

Sampling parameters for one generation request. temperature <= 0.0 means “sample nothing, take the greedy argmax” – the same deterministic behavior ferrox always had before this module existed.

Fields

temperature: f32

top_p: f32

Nucleus sampling threshold in (0.0, 1.0]. 1.0 disables top-p filtering (every token with nonzero probability is eligible).

top_k: usize

Keep only the top_k highest-probability tokens before sampling. 0 disables top-k filtering.

repetition_penalty: f32

1.0 discourages repeating a token already in history; 1.0 disables repetition penalty. Uses the standard convention (divide positive logits, multiply negative ones) so the penalty always pushes toward less likely, regardless of logit sign.

presence_penalty: f32

OpenAI-style presence penalty: subtract from logits of tokens that already appeared in history (once per distinct token).

frequency_penalty: f32

OpenAI-style frequency penalty: subtract frequency_penalty * count from logits for each token id seen in history.

Trait Implementations

impl Clone for SamplingParams

fn clone(&self) -> SamplingParams

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SamplingParams

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

Formats the value using the given formatter.

impl Default for SamplingParams

fn default() -> Self

Greedy decoding: identical behavior to ferrox’s original argmax-only generation loop.