In the generation function for text generation models there is a parameter max_time. It makes sure the generation doesn’t last longer than x seconds. It also says that it finishes current pass and then stops. But what are the referenced passes? Does the prompt go multiple times through the model?
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Control generated sequence length in characters | 0 | 439 | October 22, 2021 | |
Ensure the sentence is complete during generation | 5 | 6958 | December 19, 2024 | |
How to customize text-generation length | 1 | 907 | August 23, 2022 | |
How to pass `min_length` parameter in generate? | 1 | 327 | September 29, 2023 | |
TextGeneration Inference Model | 2 | 418 | September 22, 2023 |