# Tokenizer for 'sshleifer/distilbart-xsum-12-6'?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-for-sshleifer-distilbart-xsum-12-6%2F529%3E%5C
**Category:** Beginners\
**Created:** [July 29, 2020, 9:31pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-for-sshleifer-distilbart-xsum-12-6%2F529 "2020-07-29T21:31:57Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![chz816](https://avatars.discourse-cdn.com/v4/letter/c/3ec8ea/32.png) [@chz816](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fchz816)%5C
**Post date:** [July 29, 2020, 9:31pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-for-sshleifer-distilbart-xsum-12-6%2F529%2F1 "2020-07-29T21:31:57Z")

</div>

I try to generate outputs using `sshleifer/distilbart-xsum-12-6` but it gives me the following error:

```auto
OSError: Model name 'sshleifer/distilbart-xsum-12-6' was not found in tokenizers model name list (facebook/bart-base, facebook/bart-large, facebook/bart-large-mnli, facebook/bart-large-cnn, facebook/bart-large-xsum, yjernite/bart_eli5). We assumed 'sshleifer/distilbart-xsum-12-6' was a path or url to a directory containing vocabulary files named ['vocab.json', 'merges.txt'], but couldn't find such vocabulary files at this path or url.

```

I am thinking instead of `tokenizer = AutoTokenizer.from_pretrained("sshleifer/distilbart-xsum-12-6")` we should change it to another tokenizer for xsum? Thank you!

(Again, thank you Sam for your wonderful work.

---

<div class="post-metadata">

**Author:** ![valhalla](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/valhalla/32/4179_2.png) [@valhalla](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fvalhalla)%5C
**Post date:** [July 30, 2020, 4:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-for-sshleifer-distilbart-xsum-12-6%2F529%2F2 "2020-07-30T04:49:27Z")

</div>

> [@chz816](#):
>
> tokenizer = AutoTokenizer.from\_pretrained(“sshleifer/distilbart-xsum-12-6”)

Hi @chz816, this call should work. You can also use `BartTokenizer`

---

<div class="post-metadata">

**Author:** ![huggingfans](https://avatars.discourse-cdn.com/v4/letter/h/439d5e/32.png) [@huggingfans](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fhuggingfans)%5C
**Post date:** [August 18, 2020, 8:41pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-for-sshleifer-distilbart-xsum-12-6%2F529%2F3 "2020-08-18T20:41:13Z")

</div>

I can download the tokenizer with your code. strange.