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[]

Defined in

inference/src/tasks/nlp/textGenerationStream.ts:64

< > Update on GitHub