模型:
sileod/mdeberta-v3-base-tasksource-nli
任务:
零样本分类数据集:
xnli metaeval/xnli americas_nli MoritzLaurer/multilingual-NLI-26lang-2mil7 stsb_multi_mt paws-x miam strombergnlp/x-stance tyqiangz/multilingual-sentiments metaeval/universal-joy amazon_reviews_multi cardiffnlp/tweet_sentiment_multilingual strombergnlp/offenseval_2020 offenseval_dravidian nedjmaou/MLMA_hate_speech xglue ylacombe/xsum_factuality metaeval/x-fact pasinit/xlwic tasksource/oasst1_dense_flat papluca/language-identification wili_2018 exams xcsr xcopa juletxara/xstory_cloze Anthropic/hh-rlhf universal_dependencies tasksource/oasst1_pairwise_rlhf_reward OpenAssistant/oasst1 3AOpenAssistant/oasst1 3Atasksource/oasst1_pairwise_rlhf_reward 3Auniversal_dependencies 3AAnthropic/hh-rlhf 3Ajuletxara/xstory_cloze 3Axcopa 3Axcsr 3Aexams 3Awili_2018 3Apapluca/language-identification 3Atasksource/oasst1_dense_flat 3Apasinit/xlwic 3Ametaeval/x-fact 3Aylacombe/xsum_factuality 3Axglue 3Anedjmaou/MLMA_hate_speech 3Aoffenseval_dravidian 3Astrombergnlp/offenseval_2020 3Acardiffnlp/tweet_sentiment_multilingual 3Aamazon_reviews_multi 3Ametaeval/universal-joy 3Atyqiangz/multilingual-sentiments 3Astrombergnlp/x-stance 3Amiam 3Apaws-x 3Astsb_multi_mt 3AMoritzLaurer/multilingual-NLI-26lang-2mil7 3Aamericas_nli 3Ametaeval/xnli 3Axnli语言:
multilingual其他:
deberta-v2 文本分类 mdeberta-v3-base nli natural-language-inference multitask multi-task pipeline extreme-multi-task extreme-mtl tasksource zero-shot rlhf预印本库:
arxiv:2301.05948许可:
apache-2.0使用多语言 mdeberta-v3-base 进行 30k 步的多任务训练,用于 mtasksource 。该模型可作为进一步微调的稳定起点,或直接用于零-shot NLI 模型或零-shot pipeline。此外,您可以使用提供的 adapters 直接加载数百个任务的模型。
!pip install tasknet, tasksource -q import tasknet as tn pipe=tn.load_pipeline( 'sileod/mdeberta-v3-base-tasksource-nli', 'miam/dihana') pipe(['si','como esta?'])
更多详细信息,请参见 deberta-v3-base-tasksource-nli 并将 tasksource 替换为 mtasksource。
https://github.com/sileod/tasksource/ https://github.com/sileod/tasknet/
如需将 tasksource 集成到您的实验中,请联系 damien.sileo@inria.fr 。
更多详细信息,请参阅此 article:
@article{sileo2023tasksource, title={tasksource: Structured Dataset Preprocessing Annotations for Frictionless Extreme Multi-Task Learning and Evaluation}, author={Sileo, Damien}, url= {https://arxiv.org/abs/2301.05948}, journal={arXiv preprint arXiv:2301.05948}, year={2023} }