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