Add adapter xlm-roberta-large-sw-wiki_pfeiffer version madx

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- adapter-transformers
+- adapterhub:sw/wiki
+- xlm-roberta
+language:
+- sw
+license: "apache-2.0"
+---
+
+# Adapter `xlm-roberta-large-sw-wiki_pfeiffer` for xlm-roberta-large
+
+Pfeiffer Adapter trained with Masked Language Modelling on Swahili Wikipedia Articles for 100k steps and a batch size of 64.
+
+
+**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("xlm-roberta-large")
+adapter_name = model.load_adapter("AdapterHub/xlm-roberta-large-sw-wiki_pfeiffer")
+model.set_active_adapters(adapter_name)
+```
+
+## Architecture & Training
+
+- Adapter architecture: pfeiffer
+- Prediction head: None
+- Dataset: [sw/wiki](https://adapterhub.ml/explore/sw/wiki/)
+
+## Author Information
+
+- Author name(s): Jonas Pfeiffer
+- Author email: [email protected]
+- Author links: [Website](https://pfeiffer.ai), [GitHub](https://github.com/jopfeiff), [Twitter](https://twitter.com/@PfeiffJo)
+
+
+
+## Citation
+
+```bibtex
+@article{pfeiffer20madx,
+  title={{MAD-X}: An {A}dapter-based {F}ramework for {M}ulti-task {C}ross-lingual {T}ransfer},
+  author={Pfeiffer, Jonas and Vuli\'{c}, Ivan and Gurevych, Iryna and Ruder, Sebastian},
+  journal={arXiv preprint},
+  year={2020},
+  url={https://arxiv.org/pdf/2005.00052.pdf},
+}
+
+```
+
+*This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/xlm-roberta-large-sw-wiki_pfeiffer.yaml*.

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": "nice",
+    "inv_adapter_reduction_factor": 2,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 2,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "hidden_size": 1024,
+  "model_class": "XLMRobertaAdapterModel",
+  "model_name": "xlm-roberta-large",
+  "model_type": "xlm-roberta",
+  "name": "sw",
+  "version": "0.2.0"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e38a2ec7ed81d2d322848b67abd78880fe06ab878d96fd29a40486811035382
+size 102950018