# How to export mT5 model to onnx/torchscript and use it?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-export-mt5-model-to-onnx-torchscript-and-use-it%2F18724%3E%5C
**Category:** 🤗Transformers\
**Created:** [June 5, 2022, 8:19am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-export-mt5-model-to-onnx-torchscript-and-use-it%2F18724 "2022-06-05T08:19:37Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![tzq0301](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/tzq0301/32/4989_2.png) [@tzq0301](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftzq0301)%5C
**Post date:** [June 5, 2022, 8:19am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-export-mt5-model-to-onnx-torchscript-and-use-it%2F18724%2F1 "2022-06-05T08:19:38Z")

</div>

I have fine tuned a model named “tzq0301/mT5-news-title-generation” on the hub based on “csebuetnlp/mT5\_multilingual\_XLSum”.

I can generate my “summarization” using `model.generate(...)` but I don’t know **how to generate “summarization” using `model(...)` or `model. __call__ (...)` after exporting my model as onnx or torchscript**.

I can get `input_ids` and `attention_mask` using `tokenizer(...)`.

 ![image](https://us1.discourse-cdn.com/hellohellohello/original/2X/9/99e354f42e85e43995edba97147e31a501ad5b5f.png)

And I can get `Seq2SeqLMOutput` using `model(...)`, which contains:

- `loss=None`, `logits=tensor(...)`
- `past_key_values=tuple(tuple(tensor(...)))`
- `decoder_hidden_states=None`
- `decoder_attentions=None`
- `cross_attentions=None`
- `encoder_last_hidden_state=tensor(...)`
- `encoder_hidden_states=None`
- `encoder_attentions=None`

I don’t know how to use and which to use for my “summarization” generation.