Zero-Shot Classification
PyTorch Safetensors Transformers English deberta-v2 text-classification deberta-v3-base nli natural-language-inference multitask multi-task pipeline extreme-multi-task extreme-mtl tasksource zero-shot rlhf License: apache-2.0
Edit model card

Model Card for DeBERTa-v3-base-tasksource-nli

DeBERTa-v3-base fine-tuned with multi-task learning on 520 tasks of the tasksource collection You can further fine-tune this model to use it for any classification or multiple-choice task. This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI). The untuned model CLS embedding also has strong linear probing performance (90% on MNLI), due to the multitask training.

This is the shared model with the MNLI classifier on top. Its encoder was trained on many datasets including bigbench, Anthropic rlhf, anli... alongside many NLI and classification tasks with a SequenceClassification heads while using only one shared encoder. Each task had a specific CLS embedding, which is dropped 10% of the time to facilitate model use without it. All multiple-choice model used the same classification layers. For classification tasks, models shared weights if their labels matched. The number of examples per task was capped to 64k. The model was trained for 45k steps with a batch size of 384, and a peak learning rate of 2e-5.

The list of tasks is available in

tasksource training code:

Training took 7 days on RTX6000 24GB gpu.

Model Recycling

An earlier (weaker) version model is ranked 1st among all models with the microsoft/deberta-v3-base architecture as of 10/01/2023 Results: Evaluation on 36 datasets using sileod/deberta-v3-base_tasksource-420 as a base model yields average score of 80.45 in comparison to 79.04 by microsoft/deberta-v3-base.

20_newsgroup ag_news amazon_reviews_multi anli boolq cb cola copa dbpedia esnli financial_phrasebank imdb isear mnli mrpc multirc poem_sentiment qnli qqp rotten_tomatoes rte sst2 sst_5bins stsb trec_coarse trec_fine tweet_ev_emoji tweet_ev_emotion tweet_ev_hate tweet_ev_irony tweet_ev_offensive tweet_ev_sentiment wic wnli wsc yahoo_answers
87.042 90.9 66.46 59.7188 85.5352 85.7143 87.0566 69 79.5333 91.6735 85.8 94.324 72.4902 90.2055 88.9706 63.9851 87.5 93.6299 91.7363 91.0882 84.4765 95.0688 56.9683 91.6654 98 91.2 46.814 84.3772 58.0471 81.25 85.2326 71.8821 69.4357 73.2394 74.0385 72.2

For more information, see: Model Recycling


More details on this article:

  title={tasksource: Structured Dataset Preprocessing Annotations for Frictionless Extreme Multi-Task Learning and Evaluation},
  author={Sileo, Damien},
  url= {},
  journal={arXiv preprint arXiv:2301.05948},

Loading a specific classifier

Classifiers for all tasks available. See

Model Card Contact

Downloads last month
Hosted inference API
Zero-Shot Classification
This model can be loaded on the Inference API on-demand.

Datasets used to train sileod/deberta-v3-base-tasksource-nli

Spaces using sileod/deberta-v3-base-tasksource-nli 6