Hi. I’m working through the series of sagemaker-hugginface notebooks and it is not clear to me how the predict data is preprocess before call the model. The notebook 01_getting_started_pytorch.ipynb shows these 3 steps: preprocess datasets save datsets on s3 train the model using sagemaker Huggi…

How are the inputs tokenized when model deployment?

philschmid September 3, 2021, 9:13am 12

The Error is pretty clear. It looks like truncate is not applied correctly.
Which model are you using?

How to use fine tuned Hugging face model saved at S3 at inference time?

ClientErro:400 when using batch transformer for inference

Topic		Replies	Views
Truncation of input data for Summarization pipeline Amazon SageMaker	4	2163	November 16, 2021
Do we really preprocess the entire data set with hugging face even when we train very large language models e.g. gpt-3 size? Beginners	4	441	August 12, 2022
Questions on model's tokens 🤗Tokenizers	0	514	March 24, 2021
Access tokenizer from within predict_fn Amazon SageMaker	7	878	January 14, 2022
PyTorch models predictions varies with the same data input Models	0	440	October 27, 2022