AdapterHub/roberta-base-pf-trec

1---2tags:3- text-classification4- roberta5- adapter-transformers6datasets:7- trec8language:9- en10---11 12# Adapter `AdapterHub/roberta-base-pf-trec` for roberta-base13 14An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [trec](https://huggingface.co/datasets/trec/) dataset and includes a prediction head for classification.15 16This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.17 18## Usage19 20First, install `adapter-transformers`:21 22```23pip install -U adapter-transformers24```25_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_26 27Now, the adapter can be loaded and activated like this:28 29```python30from transformers import AutoModelWithHeads31 32model = AutoModelWithHeads.from_pretrained("roberta-base")33adapter_name = model.load_adapter("AdapterHub/roberta-base-pf-trec", source="hf")34model.active_adapters = adapter_name35```36 37## Architecture & Training38 39The training code for this adapter is available at https://github.com/adapter-hub/efficient-task-transfer.40In particular, training configurations for all tasks can be found [here](https://github.com/adapter-hub/efficient-task-transfer/tree/master/run_configs).41 42 43## Evaluation results44 45Refer to [the paper](https://arxiv.org/pdf/2104.08247) for more information on results.46 47## Citation48 49If you use this adapter, please cite our paper ["What to Pre-Train on? Efficient Intermediate Task Selection"](https://arxiv.org/pdf/2104.08247):50 51```bibtex52@inproceedings{poth-etal-2021-pre,53    title = "{W}hat to Pre-Train on? {E}fficient Intermediate Task Selection",54    author = {Poth, Clifton  and55      Pfeiffer, Jonas  and56      R{"u}ckl{'e}, Andreas  and57      Gurevych, Iryna},58    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",59    month = nov,60    year = "2021",61    address = "Online and Punta Cana, Dominican Republic",62    publisher = "Association for Computational Linguistics",63    url = "https://aclanthology.org/2021.emnlp-main.827",64    pages = "10585--10605",65}66```