Interface: TextGenerationStreamDetails
Properties
best\_of\_sequences
• Optional best_of_sequences: TextGenerationStreamBestOfSequence[]
Additional sequences when using the best_of parameter
Defined in
inference/src/tasks/nlp/textGenerationStream.ts:66
finish\_reason
• finish_reason: TextGenerationStreamFinishReason
Generation finish reason
Defined in
inference/src/tasks/nlp/textGenerationStream.ts:56
generated\_tokens
• generated_tokens: number
Number of generated tokens
Defined in
inference/src/tasks/nlp/textGenerationStream.ts:58
prefill
• prefill: TextGenerationStreamPrefillToken[]
Prompt tokens
Defined in
inference/src/tasks/nlp/textGenerationStream.ts:62
seed
• Optional seed: number
Sampling seed if sampling was activated
Defined in
inference/src/tasks/nlp/textGenerationStream.ts:60
tokens
• tokens: TextGenerationStreamToken[]