# Unable to convert output to interpretable format

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-convert-output-to-interpretable-format%2F8882%3E%5C
**Category:** 🤗Tokenizers\
**Created:** [July 31, 2021, 7:39pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-convert-output-to-interpretable-format%2F8882 "2021-07-31T19:39:37Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![markrogersjr](https://avatars.discourse-cdn.com/v4/letter/m/c4cdca/32.png) [@markrogersjr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmarkrogersjr)%5C
**Post date:** [July 31, 2021, 7:39pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-convert-output-to-interpretable-format%2F8882%2F1 "2021-07-31T19:39:37Z")

</div>

I’m not able to convert model outputs to a human-interpretable format. I went ahead and created an [issue](https://github.com/huggingface/transformers/issues/12967) along with a [PR](https://github.com/huggingface/transformers/pull/12969) that adds the feature.