---
license: apache-2.0
language:
- en
tags:
- text-generation
- text2text-generation
pipeline_tag: text2text-generation
widget:
- text: "Describe the following data: Iron Man | instance of | Superhero [SEP] Stan Lee | creator | Iron Man"
  example_title: "Example1"
- text: "Describe the following data: First Clearing | LOCATION | On NYS 52 1 Mi. Youngsville [SEP] On NYS 52 1 Mi. Youngsville | CITY_OR_TOWN | Callicoon, New York"
  example_title: "Example2"
---

# MVP-data-to-text
The MVP-data-to-text model was proposed in [**MVP: Multi-task Supervised Pre-training for Natural Language Generation**](https://github.com/RUCAIBox/MVP/blob/main/paper.pdf) by Tianyi Tang, Junyi Li, Wayne Xin Zhao and Ji-Rong Wen.

The detailed information and instructions can be found [https://github.com/RUCAIBox/MVP](https://github.com/RUCAIBox/MVP).

## Model Description
MVP-data-to-text is a prompt-based model that MVP is further equipped with prompts pre-trained using labeled data-to-text datasets. It is a variant (MVP+S) of our main MVP model. It follows a Transformer encoder-decoder architecture with layer-wise prompts.

MVP-data-to-text is specially designed for data-to-text generation tasks, such as KG-to-text generation (WebNLG, DART), table-to-text generation (WikiBio, ToTTo) and MR-to-text generation (E2E).

## Example
```python
>>> from transformers import MvpTokenizer, MvpForConditionalGeneration

>>> tokenizer = MvpTokenizer.from_pretrained("RUCAIBox/mvp")
>>> model = MvpForConditionalGeneration.from_pretrained("RUCAIBox/mvp-data-to-text")

>>> inputs = tokenizer(
...     "Describe the following data: Iron Man | instance of | Superhero [SEP] Stan Lee | creator | Iron Man",
...     return_tensors="pt",
... )
>>> generated_ids = model.generate(**inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
['Iron Man is a fictional superhero appearing in American comic books published by Marvel Comics.']
```

## Citation