| tags: | |
| - adapter-transformers | |
| - question-answering | |
| - adapterhub:qa/squad2 | |
| - bart | |
| datasets: | |
| - squad_v2 | |
| license: "apache-2.0" | |
| # Adapter `facebook-bart-large_qa_squad2_lohfink-rossi-leaveout` for facebook/bart-large | |
| **Note: This adapter was not trained by the AdapterHub team, but by these author(s): Till Lohfink & Maria Rossi (Contributed equally.). | |
| See author details below.** | |
| Adapter for bart-large using a custom architecture (Lohfink-Rossi-Leaveout) trained on the SQuAD 2.0 dataset for 15 epochs with a Cosine with Restarts learning rate scheduler ans learning rate 0.001. | |
| **This adapter was created for usage with the [Adapters](https://github.com/Adapter-Hub/adapters) library.** | |
| ## Usage | |
| First, install `adapters`: | |
| ``` | |
| pip install -U adapters | |
| ``` | |
| Now, the adapter can be loaded and activated like this: | |
| ```python | |
| from adapters import AutoAdapterModel | |
| model = AutoAdapterModel.from_pretrained("facebook/bart-large") | |
| adapter_name = model.load_adapter("AdapterHub/facebook-bart-large_qa_squad2_lohfink-rossi-leaveout") | |
| model.set_active_adapters(adapter_name) | |
| ``` | |
| ## Architecture & Training | |
| - Adapter architecture: lohfink-rossi-leaveout | |
| - Prediction head: question answering | |
| - Dataset: [SQuAD 2.0](https://rajpurkar.github.io/SQuAD-explorer/) | |
| ## Author Information | |
| - Author name(s): Till Lohfink & Maria Rossi (Contributed equally.) | |
| - Author email: tlohfink3@gatech.edu;mrossi7@gatech.edu | |
| - Author links: | |
| ## Citation | |
| ```bibtex | |
| ``` | |
| *This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/lohfink-rossi/facebook-bart-large_qa_squad2_lohfink-rossi-leaveout.yaml*. |