# Get\_all\_scores for TokenClassificationPipeline?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fget-all-scores-for-tokenclassificationpipeline%2F46091%3E%5C
**Category:** 🤗Transformers\
**Created:** [July 8, 2023, 1:18pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fget-all-scores-for-tokenclassificationpipeline%2F46091 "2023-07-08T13:18:11Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![dwmit](https://avatars.discourse-cdn.com/v4/letter/d/9de053/32.png) [@dwmit](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdwmit)%5C
**Post date:** [July 8, 2023, 1:18pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fget-all-scores-for-tokenclassificationpipeline%2F46091%2F1 "2023-07-08T13:18:12Z")

</div>

Hey everyone,

I have my own Token Classification model, that I am running with [TokenClassficationPipeline](https://huggingface.co/docs/transformers/main/main_classes/pipelines#transformers.TokenClassificationPipeline). I have got to the situation where I need to see more than only one best tag but maybe the top 3 or even all of them.

I have seen that for [TextClassificationPipeline](https://huggingface.co/docs/transformers/main/main_classes/pipelines#transformers.TextClassificationPipeline) there is a parameter named [return\_all\_scores](https://huggingface.co/docs/transformers/main/main_classes/pipelines#transformers.TextClassificationPipeline.return_all_scores). When I have tried to debug that code, I have seen that there is no option to get more than the maximal tag that fits. I have seen that [Beam Search](https://huggingface.co/blog/constrained-beam-search) can work too, but it is mainly for Seq2Seq models.

Is there any idea for getting the other possible tags’ scores that can fit? I do want to still use Pipeline since it is the most elegant solution, but if there is no other solution, I will write the code by myself.

Thanks!