# Two texts inputs for Text Classification in Inference API?

**URL:** <https://discuss.huggingface.co/t/two-texts-inputs-for-text-classification-in-inference-api/12805>\
**Category:** 🤗Hub\
**Created:** [December 14, 2021, 12:59pm UTC](https://discuss.huggingface.co/t/two-texts-inputs-for-text-classification-in-inference-api/12805 "2021-12-14T12:59:24Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![mplaza](https://avatars.discourse-cdn.com/v4/letter/m/45deac/32.png) [@mplaza](https://discuss.huggingface.co/u/mplaza)\
**Post date:** [December 14, 2021, 12:59pm UTC](https://discuss.huggingface.co/t/two-texts-inputs-for-text-classification-in-inference-api/12805/1 "2021-12-14T12:59:24Z")

</div>

Two texts inputs for Text Classification in Inference API?

Hello!,

I’ve trained a model to classify if two texts have a relation between them. Therefore I need to introduce two independent strings as input.  
As I’m using the tokenizer I can introduce two strings as input for the model using code, however I cannot reproduce that functionality in “Hosted Inference API”.

```auto
tokenizer = AutoTokenizer.from_pretrained("my-model")
model = AutoModelForSequenceClassification.from_pretrained("my-model")

input = tokenizer('I love you','I like you',return_tensors='pt')
model(**input)

```

When calling tokenizer with two separated strings the token type id distinguishes between text 1 and 2:

```auto
{'input_ids': tensor([[101, 1045, 2293, 2017, 102, 1045, 2066, 2017, 102]]), 'token_type_ids': tensor([[0, 0, 0, 0, 0, 1, 1, 1, 1]]), 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1]])}

```

However using just one string and [SEP] this is not the case, and the behaviour is the same as in “Inference API”

```auto
{'input_ids': tensor([[101, 1045, 2293, 2017, 101, 1045, 2066, 2017, 102]]), 'token_type_ids': tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0]]), 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1]])}

```

Would it be possible to add a second input text to “Hosted Inference API” in order to reproduce the same behaviour that code allows?

Thanks!

---

<div class="post-metadata">

**Author:** ![merve](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/merve/32/49809_2.png) [@merve](https://discuss.huggingface.co/u/merve)\
**Post date:** [January 2, 2022, 10:30am UTC](https://discuss.huggingface.co/t/two-texts-inputs-for-text-classification-in-inference-api/12805/2 "2022-01-02T10:30:50Z")

</div>

Hello,

You’re right that text classification hosted widget only takes one text and there are text classification models taking multiple text inputs. I opened an feature request to have a more flexible behavior. In the meanwhile if you want this for demonstration purposes, you can create a Space based on your model.