# Helsinki-NLP/opus-mt-en-fr missing tf\_model.h5

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelsinki-nlp-opus-mt-en-fr-missing-tf-model-h5%2F13486%3E%5C
**Category:** Course\
**Created:** [January 8, 2022, 2:02am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelsinki-nlp-opus-mt-en-fr-missing-tf-model-h5%2F13486 "2022-01-08T02:02:48Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![nickmuchi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nickmuchi/32/29420_2.png) [@nickmuchi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnickmuchi)%5C
**Post date:** [January 8, 2022, 2:02am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelsinki-nlp-opus-mt-en-fr-missing-tf-model-h5%2F13486%2F1 "2022-01-08T02:02:48Z")

</div>

Hi there,

I have been following the tensorflow track of the HF course and got an http 404 error when running the below:

```auto
from transformers import TFAutoModelForSeq2SeqLM

model = TFAutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)

```

error message:

404 Client Error: Not Found for url: [https://huggingface.co/Helsinki-NLP/opus-mt-en-fr/resolve/main/tf\_model.h5](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr/resolve/main/tf_model.h5)

I went to the model card and could not find the tf\_model.h5 file. Is there something that I am missing or does the model only work for Torch?

thanks

---

<div class="post-metadata">

**Author:** ![lewtun](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/lewtun/32/30995_2.png) [@lewtun](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flewtun)%5C
**Post date:** [January 17, 2022, 3:51pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelsinki-nlp-opus-mt-en-fr-missing-tf-model-h5%2F13486%2F2 "2022-01-17T15:51:08Z")

</div>

Hi @nickmuchi, thanks for the bug report!

Indeed, you’re right that this model only has weights for PyTorch. However, you can load it in TensorFlow using the `from_pt` argument as follows:

```python
from transformers import TFAutoModelForSeq2SeqLM

model = TFAutoModelForSeq2SeqLM.from_pretrained(model_checkpoint, from_pt=True)

```

In the meantime, I’ll post a fix on the website - thanks!

---

<div class="post-metadata">

**Author:** ![nickmuchi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nickmuchi/32/29420_2.png) [@nickmuchi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnickmuchi)%5C
**Post date:** [January 17, 2022, 10:20pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelsinki-nlp-opus-mt-en-fr-missing-tf-model-h5%2F13486%2F3 "2022-01-17T22:20:03Z")

</div>

That worked, thank you very much!
