Struct ModelOverride 

pub struct ModelOverride {

    pub context_length: Option<u32>,
    pub batch_size: Option<u32>,
    pub ubatch_size: Option<u32>,
    pub cache_type_k: Option<CacheTypeK>,
    pub cache_type_v: Option<CacheTypeV>,
    pub keep: Option<i32>,
    pub swa_full: Option<bool>,
    pub mlock: Option<bool>,
    pub mmap: Option<bool>,
    pub numa: Option<NumMode>,
    pub uniform_cache: Option<bool>,
    pub system_prompt: Option<String>,
    pub system_prompt_preset_name: Option<String>,
    pub max_concurrent_predictions: Option<u32>,
    pub threads: Option<u32>,
    pub threads_batch: Option<u32>,
    pub parallel: Option<u32>,
    pub gpu_layers: Option<i32>,
    pub split_mode: Option<SplitMode>,
    pub tensor_split: Option<String>,
    pub main_gpu: Option<i32>,
    pub fit: Option<bool>,
    pub lora: Option<PathBuf>,
    pub lora_scaled: Option<(PathBuf, f32)>,
    pub rpc: Option<String>,
    pub embedding: Option<bool>,
    pub kv_cache_offload: Option<bool>,
    pub flash_attn: Option<bool>,
    pub jinja: Option<bool>,
    pub chat_template: Option<String>,
    pub chat_template_kwargs: Option<String>,
    pub expert_count: Option<i32>,
    pub gpu_layers_mode: Option<GpuLayersMode>,
    pub seed: Option<i32>,
    pub temperature: Option<f32>,
    pub top_k: Option<i32>,
    pub top_p: Option<f32>,
    pub min_p: Option<f32>,
    pub typical_p: Option<f32>,
    pub mirostat: Option<Mirostat>,
    pub mirostat_lr: Option<f32>,
    pub mirostat_ent: Option<f32>,
    pub ignore_eos: Option<bool>,
    pub samplers: Option<Samplers>,
    pub repeat_penalty: Option<f32>,
    pub repeat_last_n: Option<i32>,
    pub presence_penalty: Option<f32>,
    pub frequency_penalty: Option<f32>,
    pub dry_multiplier: Option<f32>,
    pub dry_base: Option<f32>,
    pub dry_allowed_length: Option<i32>,
    pub dry_penalty_last_n: Option<i32>,
    pub rope_scaling: Option<RopeScaling>,
    pub rope_scale: Option<f32>,
    pub rope_freq_base: Option<f32>,
    pub rope_freq_scale: Option<f32>,
    pub rope_yarn_enabled: Option<bool>,
    pub cache_prompt: Option<bool>,
    pub cache_reuse: Option<u32>,
    pub webui: Option<bool>,
    pub max_tokens: Option<u32>,
    pub cache_type: Option<CacheType>,
    pub llama_cpp_version_cpu: Option<String>,
    pub llama_cpp_version_vulkan: Option<String>,
    pub llama_cpp_version_rocm: Option<String>,
    pub llama_cpp_version_rocm_lemonade: Option<String>,
    pub llama_cpp_version_cuda: Option<String>,
    pub spec_type: Option<String>,
    pub draft_tokens: Option<u32>,
    pub tags: Option<Vec<String>>,
}

Fields

context_length: Option<u32>

batch_size: Option<u32>

ubatch_size: Option<u32>

cache_type_k: Option<CacheTypeK>

cache_type_v: Option<CacheTypeV>

keep: Option<i32>

swa_full: Option<bool>

mlock: Option<bool>

mmap: Option<bool>

numa: Option<NumMode>

uniform_cache: Option<bool>

system_prompt: Option<String>

system_prompt_preset_name: Option<String>

max_concurrent_predictions: Option<u32>

threads: Option<u32>

threads_batch: Option<u32>

parallel: Option<u32>

gpu_layers: Option<i32>

split_mode: Option<SplitMode>

tensor_split: Option<String>

main_gpu: Option<i32>

fit: Option<bool>

lora: Option<PathBuf>

lora_scaled: Option<(PathBuf, f32)>

rpc: Option<String>

embedding: Option<bool>

kv_cache_offload: Option<bool>

flash_attn: Option<bool>

jinja: Option<bool>

chat_template: Option<String>

chat_template_kwargs: Option<String>

expert_count: Option<i32>

gpu_layers_mode: Option<GpuLayersMode>

seed: Option<i32>

temperature: Option<f32>

top_k: Option<i32>

top_p: Option<f32>

min_p: Option<f32>

typical_p: Option<f32>

mirostat: Option<Mirostat>

mirostat_lr: Option<f32>

mirostat_ent: Option<f32>

ignore_eos: Option<bool>

samplers: Option<Samplers>

repeat_penalty: Option<f32>

repeat_last_n: Option<i32>

presence_penalty: Option<f32>

frequency_penalty: Option<f32>

dry_multiplier: Option<f32>

dry_base: Option<f32>

dry_allowed_length: Option<i32>

dry_penalty_last_n: Option<i32>

rope_scaling: Option<RopeScaling>

rope_scale: Option<f32>

rope_freq_base: Option<f32>

rope_freq_scale: Option<f32>

rope_yarn_enabled: Option<bool>

cache_prompt: Option<bool>

cache_reuse: Option<u32>

webui: Option<bool>

max_tokens: Option<u32>

cache_type: Option<CacheType>

llama_cpp_version_cpu: Option<String>

llama_cpp_version_vulkan: Option<String>

llama_cpp_version_rocm: Option<String>

llama_cpp_version_rocm_lemonade: Option<String>

llama_cpp_version_cuda: Option<String>

spec_type: Option<String>

draft_tokens: Option<u32>

tags: Option<Vec<String>>

Implementations

impl ModelOverride

pub fn from_settings(s: &ModelSettings) -> Self

pub fn apply(&self, base: &mut ModelSettings)

Merge override into a base ModelSettings (in-place).

Trait Implementations

impl Clone for ModelOverride

fn clone(&self) -> ModelOverride

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelOverride

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

Formats the value using the given formatter.

impl Default for ModelOverride

fn default() -> ModelOverride

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelOverride

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ModelOverride

fn eq(&self, other: &ModelOverride) -> 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 Serialize for ModelOverride

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelOverride