Struct ConversationConfig

pub struct ConversationConfig {

    pub model_type: ModelType,
    pub model_resource: ModelResource,
    pub config_resource: Box<dyn ResourceProvider + Send>,
    pub vocab_resource: Box<dyn ResourceProvider + Send>,
    pub merges_resource: Option<Box<dyn ResourceProvider + Send>>,
    pub min_length: i64,
    pub max_length: Option<i64>,
    pub min_length_for_response: i64,
    pub do_sample: bool,
    pub early_stopping: bool,
    pub num_beams: i64,
    pub temperature: f64,
    pub top_k: i64,
    pub top_p: f64,
    pub repetition_penalty: f64,
    pub length_penalty: f64,
    pub no_repeat_ngram_size: i64,
    pub num_return_sequences: i64,
    pub num_beam_groups: Option<i64>,
    pub diversity_penalty: Option<f64>,
    pub device: Device,
    pub kind: Option<Kind>,
}

Configuration for multi-turn classification

Contains information regarding the model to load, mirrors the GenerationConfig, with a different set of default parameters and sets the device to place the model on.

Fields

model_type: ModelType

Model type

model_resource: ModelResource

Model weights resource (default: DialoGPT-medium)

config_resource: Box<dyn ResourceProvider + Send>

Config resource (default: DialoGPT-medium)

vocab_resource: Box<dyn ResourceProvider + Send>

Vocab resource (default: DialoGPT-medium)

merges_resource: Option<Box<dyn ResourceProvider + Send>>

Merges resource (default: DialoGPT-medium)

min_length: i64

Minimum sequence length (default: 0)

max_length: Option<i64>

Maximum sequence length (default: 20)

min_length_for_response: i64

Minimum free length available for generated responses (default: 32)

do_sample: bool

Sampling flag. If true, will perform top-k and/or nucleus sampling on generated tokens, otherwise greedy (deterministic) decoding (default: true)

early_stopping: bool

Early stopping flag indicating if the beam search should stop as soon as num_beam hypotheses have been generated (default: false)

num_beams: i64

Number of beams for beam search (default: 5)

temperature: f64

Temperature setting. Values higher than 1 will improve originality at the risk of reducing relevance (default: 1.0)

top_k: i64

Top_k values for sampling tokens. Value higher than 0 will enable the feature (default: 0)

top_p: f64

Top_p value for Nucleus sampling, Holtzman et al.. Keep top tokens until cumulative probability reaches top_p (default: 0.9)

repetition_penalty: f64

Repetition penalty (mostly useful for CTRL decoders). Values higher than 1 will penalize tokens that have been already generated. (default: 1.0)

length_penalty: f64

Exponential penalty based on the length of the hypotheses generated (default: 1.0)

no_repeat_ngram_size: i64

Number of allowed repetitions of n-grams. Values higher than 0 turn on this feature (default: 3)

num_return_sequences: i64

Number of sequences to return for each prompt text (default: 1)

num_beam_groups: Option<i64>

Number of beam groups for diverse beam generation. If provided and higher than 1, will split the beams into beam subgroups leading to more diverse generation.

diversity_penalty: Option<f64>

Diversity penalty for diverse beam search. High values will enforce more difference between beam groups (default: 5.5)

device: Device

Device to place the model on (default: CUDA/GPU when available)

kind: Option<Kind>

Model weights precision. If not provided, will default to full precision on CPU, or the loaded weights precision otherwise

Trait Implementations

impl Default for ConversationConfig

fn default() -> ConversationConfig

Returns the “default value” for a type.

impl From<ConversationConfig> for GenerateConfig

fn from(config: ConversationConfig) -> GenerateConfig

Converts to this type from the input type.