# Inference Hyperparameters

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-hyperparameters%2F9539%3E%5C
**Category:** Amazon SageMaker\
**Created:** [August 27, 2021, 7:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-hyperparameters%2F9539 "2021-08-27T19:45:26Z")\
**Posts on this page:** 1\
**Showing post:** 10

<div class="post-metadata">

**Author:** ![Oigres](https://avatars.discourse-cdn.com/v4/letter/o/a8b319/32.png) [@Oigres](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FOigres)%5C
**Post date:** [September 15, 2021, 1:35pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-hyperparameters%2F9539%2F10 "2021-09-15T13:35:31Z")

</div>

Okay.

[Here](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-are-the-inputs-tokenized-when-model-deployment%2F9692%2F6) you suggested to me to add the `Truncation` parameter. This is a parameter related with the tokenizer. Why it can be used as “pipeline parameter”. I’m looking for a solution like:

```python
parameters = {
                  'truncation': True,
                  'max_length': 256,
                  'padding': True,
}

```

But I don’t know if the names are right or they aren’t (except `Truncation`, since you suggested the name). Seems that “max\_length” parameter has not any effect on predictions because such predictions are exactly the same with different values.

---

_[View the full topic](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-hyperparameters%2F9539)._