TextGenerationConfig - Inworld AI Documentation

Properties

max_new_tokens?: string | number

Maximum number of tokens to generate

max_prompt_length?: string | number

Maximum length of the prompt in tokens

temperature?: string | number

Controls randomness of generated text

top_p?: string | number

Probability for most probable tokens sampling

repetition_penalty?: string | number

Repetition penalty

frequency_penalty?: string | number

Frequency penalty

presence_penalty?: string | number

Presence penalty

stop_sequences?: string[]

List of sequences to stop generation

seed?: string | number

Random seed for controlling the randomness of text generation

logit_bias?: object

Logit bias to modify token likelihood