Huggingface.js documentation

Interface: TextGenerationStreamBestOfSequence

Huggingface.js

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Interface: TextGenerationStreamBestOfSequence

Properties

finish _ reason

• finish_reason: TextGenerationStreamFinishReason

Generation finish reason

Defined in

inference/src/tasks/nlp/textGenerationStream.ts:35

generated _ text

• generated_text: string

Generated text

Defined in

inference/src/tasks/nlp/textGenerationStream.ts:33

generated _ tokens

• generated_tokens: number

Number of generated tokens

Defined in

inference/src/tasks/nlp/textGenerationStream.ts:37

prefill

• prefill: TextGenerationStreamPrefillToken[]

Prompt tokens

Defined in

inference/src/tasks/nlp/textGenerationStream.ts:41

seed

• Optional seed: number

Sampling seed if sampling was activated

Defined in

inference/src/tasks/nlp/textGenerationStream.ts:39

tokens

• tokens: TextGenerationStreamToken[]

Generated tokens

Defined in

inference/src/tasks/nlp/textGenerationStream.ts:43

< > Update on GitHub

←TextGenerationOutput TextGenerationStreamDetails→