Hugging Face's logo

RUCAIBox
/
mvp-multi-task

Text2Text Generation
Transformers
PyTorch
English
mvp
text-generation
summarization
conversational
Inference Endpoints
Model card Files Community
1

MVP-multi-task

The MVP-multi-task model was proposed in MVP: Multi-task Supervised Pre-training for Natural Language Generation 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.

Model Description

MVP-multi-task is a prompt-based model that MVP is further equipped with prompts pre-trained using a mixture of labeled datasets. It is a variant (MVP+M) of our main MVP model. It follows a Transformer encoder-decoder architecture with layer-wise prompts.

MVP is specially designed for natural language generation and can be adapted to a wide range of generation tasks, including but not limited to summarization, data-to-text generation, open-ended dialogue system, story generation, question answering, question generation, task-oriented dialogue system, commonsense generation, paraphrase generation, text style transfer, and text simplification. Our model can also be adapted to natural language understanding tasks such as sequence classification and (extractive) question answering.

Example

For summarization:

>>> from transformers import MvpTokenizer, MvpForConditionalGeneration

>>> tokenizer = MvpTokenizer.from_pretrained("RUCAIBox/mvp")
>>> model = MvpForConditionalGeneration.from_pretrained("RUCAIBox/mvp-multi-task")

>>> inputs = tokenizer(
...     "Summarize: You may want to stick it to your boss and leave your job, but don't do it if these are your reasons.",
...     return_tensors="pt",
... )
>>> generated_ids = model.generate(**inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
["Why You Shouldn't Quit Your Job"]

For data-to-text generation:

>>> from transformers import MvpTokenizerFast, MvpForConditionalGeneration

>>> tokenizer = MvpTokenizerFast.from_pretrained("RUCAIBox/mvp")
>>> model = MvpForConditionalGeneration.from_pretrained("RUCAIBox/mvp-multi-task")

>>> 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.']

Related Models

MVP: https://huggingface.co/RUCAIBox/mvp.

Prompt-based models:

Multi-task models:

Citation 

@article{tang2022mvp,
  title={MVP: Multi-task Supervised Pre-training for Natural Language Generation},
  author={Tang, Tianyi and Li, Junyi and Zhao, Wayne Xin and Wen, Ji-Rong},
  journal={arXiv preprint arXiv:2206.12131},
  year={2022},
  url={https://arxiv.org/abs/2206.12131},
}
Downloads last month
6
Inference Examples
Text2Text Generation
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.