How are the inputs tokenized when model deployment?

philschmid · September 3, 2021, 9:15am

Oigres:

{"inputs": "long sentence 1", "parameters": {"trucation": true}} 
{"inputs": "long sentence 2", "parameters": {"trucation": true}}
{"inputs": "long sentence 3", "parameters": {"trucation": true}}
{"inputs": "long sentence 4", "parameters": {"trucation": true}}

I just noticed you have a spelling mistake in truncation → trucation is wrong

Topic		Replies	Views
Inference Hyperparameters Amazon SageMaker	29	4905	October 8, 2021
Access Tokenizer from Sagemaker BART Endpoint Amazon SageMaker	4	1027	November 29, 2022
Access tokenizer from within predict_fn Amazon SageMaker	7	1044	January 14, 2022
ClientErro:400 when using batch transformer for inference Amazon SageMaker	11	2249	January 13, 2022
Errors: Batch transform on fine-tuned models Amazon SageMaker	4	1593	May 4, 2023

How are the inputs tokenized when model deployment?

Related topics