Hugging Face's logo

RUCAIBox
/
mtl-question-answering

Text2Text Generation
Transformers
PyTorch
English
mvp
text-generation
Inference Endpoints
Model card Files Community
mtl-question-answering / README.md
StevenTang's picture
StevenTang
Update README
bc7e726
preview code
|
raw
history blame contribute delete
4.31 kB
metadata
license: apache-2.0
language:
  - en
tags:
  - text-generation
  - text2text-generation
pipeline_tag: text2text-generation
widget:
  - text: >-
      Answer the following question: From which country did Angola achieve
      independence in 1975?
    example_title: Example1
  - text: >-
      Answer the following question: what is ce certified [X_SEP] The CE marking
      is the manufacturer's declaration that the product meets the requirements
      of the applicable EC directives. Officially, CE is an abbreviation of
      Conformite Conformité, europeenne Européenne Meaning. european conformity
    example_title: Example2

MTL-question-answering

The MTL-question-answering 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

MTL-question-answering is supervised pre-trained using a mixture of labeled question answering datasets. It is a variant (Single) of our main MVP model. It follows a standard Transformer encoder-decoder architecture.

MTL-question-answering is specially designed for question answering tasks, such as reading comprehension (SQuAD), conversational question answering (CoQA) and closed-book question-answering (Natural Questions).

Example 

>>> from transformers import MvpTokenizer, MvpForConditionalGeneration

>>> tokenizer = MvpTokenizer.from_pretrained("RUCAIBox/mvp")
>>> model = MvpForConditionalGeneration.from_pretrained("RUCAIBox/mtl-question-answering")

>>> inputs = tokenizer(
...     "Answer the following question: From which country did Angola achieve independence in 1975?",
...     return_tensors="pt",
... )
>>> generated_ids = model.generate(**inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
['Portugal']

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},
}