# Seq2Seq Encoder Decoder model Tensorflow

**URL:** <https://discuss.huggingface.co/t/seq2seq-encoder-decoder-model-tensorflow/3272>\
**Category:** 🤗Transformers\
**Created:** [January 19, 2021, 1:15am UTC](https://discuss.huggingface.co/t/seq2seq-encoder-decoder-model-tensorflow/3272 "2021-01-19T01:15:45Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![jominmathew](https://avatars.discourse-cdn.com/v4/letter/j/76d3ee/32.png) [@jominmathew](https://discuss.huggingface.co/u/jominmathew)\
**Post date:** [January 19, 2021, 1:15am UTC](https://discuss.huggingface.co/t/seq2seq-encoder-decoder-model-tensorflow/3272/1 "2021-01-19T01:15:45Z")

</div>

Can anyone help me to find Encoder Decoder implementation in Tensorflow. All HF models seems to be in PyTorch?

---

<div class="post-metadata">

**Author:** ![Jung](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/jung/32/21989_2.png) [@Jung](https://discuss.huggingface.co/u/Jung)\
**Post date:** [January 19, 2021, 3:07am UTC](https://discuss.huggingface.co/t/seq2seq-encoder-decoder-model-tensorflow/3272/2 "2021-01-19T03:07:08Z")

</div>

We do have important most-used seq2seq models like T5 and Bart in Tensorflow

[https://huggingface.co/transformers/model\_doc/t5.html#tft5forconditionalgeneration](https://huggingface.co/transformers/model_doc/t5.html#tft5forconditionalgeneration)

[https://huggingface.co/transformers/model\_doc/bart.html#tfbartforconditionalgeneration](https://huggingface.co/transformers/model_doc/bart.html#tfbartforconditionalgeneration)

[https://huggingface.co/transformers/model\_doc/led.html#tfledmodel](https://huggingface.co/transformers/model_doc/led.html#tfledmodel)

---

<div class="post-metadata">

**Author:** ![jominmathew](https://avatars.discourse-cdn.com/v4/letter/j/76d3ee/32.png) [@jominmathew](https://discuss.huggingface.co/u/jominmathew)\
**Post date:** [January 19, 2021, 6:04am UTC](https://discuss.huggingface.co/t/seq2seq-encoder-decoder-model-tensorflow/3272/3 "2021-01-19T06:04:05Z")

</div>

Thank you. But I was looking for Encoder Dcoder ( Roberta2Roberta ) whch @patrickvonplaten has used for summarisation. The nitebok is in PyTorch, do we have the same / similar in tensorfow.

---

<div class="post-metadata">

**Author:** ![valhalla](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/valhalla/32/4179_2.png) [@valhalla](https://discuss.huggingface.co/u/valhalla)\
**Post date:** [January 19, 2021, 6:17am UTC](https://discuss.huggingface.co/t/seq2seq-encoder-decoder-model-tensorflow/3272/4 "2021-01-19T06:17:43Z")

</div>

hi @jominmathew  
`EncoderDecoder` is currently not implemented in TF, it’s planned but I’m afraid I don’t know the ETA

---

<div class="post-metadata">

**Author:** ![s4sarath](https://avatars.discourse-cdn.com/v4/letter/s/bc79bd/32.png) [@s4sarath](https://discuss.huggingface.co/u/s4sarath)\
**Post date:** [January 19, 2021, 3:36pm UTC](https://discuss.huggingface.co/t/seq2seq-encoder-decoder-model-tensorflow/3272/5 "2021-01-19T15:36:43Z")

</div>

@jominmathew - The support for Tensorflow is minimal in hugginface as of now. I think some good updates will be coming soon.