# Vanilla Transformer

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvanilla-transformer%2F18127%3E%5C
**Category:** Beginners\
**Created:** [May 19, 2022, 2:22am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvanilla-transformer%2F18127 "2022-05-19T02:22:55Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Onlydrinkwater](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/onlydrinkwater/32/3503_2.png) [@Onlydrinkwater](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FOnlydrinkwater)%5C
**Post date:** [May 19, 2022, 2:22am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvanilla-transformer%2F18127%2F1 "2022-05-19T02:22:55Z")

</div>

Hi all,

Is the transformer model and tokenizer used in the paper ‘Attention is all you need’ available in HF?

I want to reproduce the result in the paper.  
( ‘We use Transformer (Vaswani et al., 2017) as the basic model structure’)  
They got 28.4 bleu score using the basic transformer model on en-de task.

Any help will be appreciated!

---

<div class="post-metadata">

**Author:** ![DevavratSinghBisht](https://avatars.discourse-cdn.com/v4/letter/d/4491bb/32.png) [@DevavratSinghBisht](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDevavratSinghBisht)%5C
**Post date:** [June 6, 2023, 6:10am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvanilla-transformer%2F18127%2F2 "2023-06-06T06:10:30Z")

</div>

Hi @Onlydrinkwater ,

Were you able to get the implementation of the model and tokenizer ?  
If yes then can you please share it with me.  
Also, if you were able to replicate the results, can you please share any tips and tricks to do the same.