Struct rust_bert::gpt2::GPT2Generator [−][src]
pub struct GPT2Generator { /* fields omitted */ }
Expand description
Implementations
Build a new GPT2Generator
Arguments
generate_config
-GenerateConfig
object containing the resource references (model, vocabulary, configuration), generation options and device placement (CPU/GPU)
Example
use rust_bert::gpt2::GPT2Generator;
use rust_bert::pipelines::generation_utils::GenerateConfig;
let generate_config = GenerateConfig {
max_length: 30,
do_sample: true,
num_beams: 5,
temperature: 1.1,
num_return_sequences: 3,
..Default::default()
};
let gpt2_generator = GPT2Generator::new(generate_config)?;
Trait Implementations
Generate text based on a vector of promp texts. Read more
Generate token indices without decoding (useful for token-level operations before returning final text or as validation step during training). Read more
fn generate_from_ids_and_past(
&self,
input_ids: Tensor,
attention_mask: Option<Tensor>,
generate_options: Option<GenerateOptions<'_>>
) -> Vec<GeneratedIndicesOutput>ⓘ
fn generate_from_ids_and_past(
&self,
input_ids: Tensor,
attention_mask: Option<Tensor>,
generate_options: Option<GenerateOptions<'_>>
) -> Vec<GeneratedIndicesOutput>ⓘ
Generate token indices given a list of indices (useful when the input has been pre-tokenized). Returns a list of output tokens that need to be decoded using a tokenizer. Read more
Returns a reference to the text generator’s tokenizer Read more
Auto Trait Implementations
impl RefUnwindSafe for GPT2Generator
impl Send for GPT2Generator
impl !Sync for GPT2Generator
impl Unpin for GPT2Generator
impl UnwindSafe for GPT2Generator
Blanket Implementations
Mutably borrows from an owned value. Read more
Instruments this type with the provided Span
, returning an
Instrumented
wrapper. Read more
type Output = T
type Output = T
Should always be Self