Struct ModelOptions

pub struct ModelOptions { /* private fields */ }

Implementations

impl ModelOptions

pub fn mirostat(self, mirostat: u8) -> Self

Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)

pub fn mirostat_eta(self, mirostat_eta: f32) -> Self

Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1)

pub fn mirostat_tau(self, mirostat_tau: f32) -> Self

Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)

pub fn num_ctx(self, num_ctx: u64) -> Self

Sets the size of the context window used to generate the next token. (Default: 2048)

pub fn num_gqa(self, num_gqa: u32) -> Self

The number of GQA groups in the transformer layer. Required for some models, for example it is 8 for llama2:70b

pub fn num_gpu(self, num_gpu: u32) -> Self

The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable.

pub fn num_thread(self, num_thread: u32) -> Self

Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number of cores).

pub fn repeat_last_n(self, repeat_last_n: i32) -> Self

Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)

pub fn repeat_penalty(self, repeat_penalty: f32) -> Self

Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)

pub fn temperature(self, temperature: f32) -> Self

The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)

pub fn seed(self, seed: i32) -> Self

Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0)

pub fn stop(self, stop: Vec<String>) -> Self

Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate stop parameters in a modelfile.

pub fn tfs_z(self, tfs_z: f32) -> Self

Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)

pub fn num_predict(self, num_predict: i32) -> Self

Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context)

pub fn top_k(self, top_k: u32) -> Self

Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)

pub fn top_p(self, top_p: f32) -> Self

Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)

Trait Implementations

impl Clone for ModelOptions

fn clone(&self) -> ModelOptions

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelOptions

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

Formats the value using the given formatter.

impl Default for ModelOptions

fn default() -> ModelOptions

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelOptions

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ModelOptions

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.