research-backup / mbart-large-cc25-jaquad-qag

huggingface.co
Total runs: 20
24-hour runs: 0
7-day runs: 0
30-day runs: 9
Model's Last Updated: January 18 2023
text-generation

Introduction of mbart-large-cc25-jaquad-qag

Model Details of mbart-large-cc25-jaquad-qag

Model Card of lmqg/mbart-large-cc25-jaquad-qag

This model is fine-tuned version of facebook/mbart-large-cc25 for question & answer pair generation task on the lmqg/qag_jaquad (dataset_name: default) via lmqg .

Overview
Usage
from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="ja", model="lmqg/mbart-large-cc25-jaquad-qag")

# model prediction
question_answer_pairs = model.generate_qa("フェルメールの作品では、17世紀のオランダの画家、ヨハネス・フェルメールの作品について記述する。フェルメールの作品は、疑問作も含め30数点しか現存しない。現存作品はすべて油彩画で、版画、下絵、素描などは残っていない。")
  • With transformers
from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/mbart-large-cc25-jaquad-qag")
output = pipe("ゾフィーは貴族出身ではあったが王族出身ではなく、ハプスブルク家の皇位継承者であるフランツ・フェルディナントとの結婚は貴賤結婚となった。皇帝フランツ・ヨーゼフは、2人の間に生まれた子孫が皇位を継がないことを条件として結婚を承認していた。視察が予定されている6月28日は2人の14回目の結婚記念日であった。")
Evaluation
Score Type Dataset
QAAlignedF1Score (BERTScore) 72.68 default lmqg/qag_jaquad
QAAlignedF1Score (MoverScore) 51.93 default lmqg/qag_jaquad
QAAlignedPrecision (BERTScore) 71.67 default lmqg/qag_jaquad
QAAlignedPrecision (MoverScore) 51.31 default lmqg/qag_jaquad
QAAlignedRecall (BERTScore) 73.79 default lmqg/qag_jaquad
QAAlignedRecall (MoverScore) 52.62 default lmqg/qag_jaquad
Training hyperparameters

The following hyperparameters were used during fine-tuning:

  • dataset_path: lmqg/qag_jaquad
  • dataset_name: default
  • input_types: ['paragraph']
  • output_types: ['questions_answers']
  • prefix_types: None
  • model: facebook/mbart-large-cc25
  • max_length: 512
  • max_length_output: 256
  • epoch: 11
  • batch: 8
  • lr: 0.0001
  • fp16: False
  • random_seed: 1
  • gradient_accumulation_steps: 8
  • label_smoothing: 0.0

The full configuration can be found at fine-tuning config file .

Citation
@inproceedings{ushio-etal-2022-generative,
    title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
    author = "Ushio, Asahi  and
        Alva-Manchego, Fernando  and
        Camacho-Collados, Jose",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, U.A.E.",
    publisher = "Association for Computational Linguistics",
}

Runs of research-backup mbart-large-cc25-jaquad-qag on huggingface.co

20
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
9
30-day runs

More Information About mbart-large-cc25-jaquad-qag huggingface.co Model

More mbart-large-cc25-jaquad-qag license Visit here:

https://choosealicense.com/licenses/cc-by-4.0

mbart-large-cc25-jaquad-qag huggingface.co

mbart-large-cc25-jaquad-qag huggingface.co is an AI model on huggingface.co that provides mbart-large-cc25-jaquad-qag's model effect (), which can be used instantly with this research-backup mbart-large-cc25-jaquad-qag model. huggingface.co supports a free trial of the mbart-large-cc25-jaquad-qag model, and also provides paid use of the mbart-large-cc25-jaquad-qag. Support call mbart-large-cc25-jaquad-qag model through api, including Node.js, Python, http.

mbart-large-cc25-jaquad-qag huggingface.co Url

https://huggingface.co/research-backup/mbart-large-cc25-jaquad-qag

research-backup mbart-large-cc25-jaquad-qag online free

mbart-large-cc25-jaquad-qag huggingface.co is an online trial and call api platform, which integrates mbart-large-cc25-jaquad-qag's modeling effects, including api services, and provides a free online trial of mbart-large-cc25-jaquad-qag, you can try mbart-large-cc25-jaquad-qag online for free by clicking the link below.

research-backup mbart-large-cc25-jaquad-qag online free url in huggingface.co:

https://huggingface.co/research-backup/mbart-large-cc25-jaquad-qag

mbart-large-cc25-jaquad-qag install

mbart-large-cc25-jaquad-qag is an open source model from GitHub that offers a free installation service, and any user can find mbart-large-cc25-jaquad-qag on GitHub to install. At the same time, huggingface.co provides the effect of mbart-large-cc25-jaquad-qag install, users can directly use mbart-large-cc25-jaquad-qag installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

mbart-large-cc25-jaquad-qag install url in huggingface.co:

https://huggingface.co/research-backup/mbart-large-cc25-jaquad-qag

Url of mbart-large-cc25-jaquad-qag

mbart-large-cc25-jaquad-qag huggingface.co Url

Provider of mbart-large-cc25-jaquad-qag huggingface.co

research-backup
ORGANIZATIONS

Other API from research-backup