Add adapter roberta-base-sst_pfeiffer version AdapterFusion

README.md

@@ -0,0 +1,61 @@
+---
+tags:
+- adapter-transformers
+- adapterhub:sentiment/sst-2
+- roberta
+license: "apache-2.0"
+---
+
+# Adapter `roberta-base-sst_pfeiffer` for roberta-base
+
+Pfeiffer Adapter trained on the SST-2 task.
+
+
+**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("roberta-base")
+adapter_name = model.load_adapter("AdapterHub/roberta-base-sst_pfeiffer")
+model.set_active_adapters(adapter_name)
+```
+
+## Architecture & Training
+
+- Adapter architecture: pfeiffer
+- Prediction head: None
+- Dataset: [SST-2](https://nlp.stanford.edu/sentiment/index.html)
+
+## 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{Pfeiffer2020AdapterFusion,
+author = {Pfeiffer, Jonas and Kamath, Aishwarya and R{\"{u}}ckl{\'{e}}, Andreas and Cho, Kyunghyun and Gurevych, Iryna},
+journal = {arXiv preprint},
+title = {{AdapterFusion}:  Non-Destructive Task Composition for Transfer Learning},
+ url       = {https://arxiv.org/pdf/2005.00247.pdf},
+year = {2020}
+}
+
+```
+
+*This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/roberta-base-sst_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": null,
+    "inv_adapter_reduction_factor": null,
+    "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": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "sst_glue",
+  "version": "0.2.0"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5b4bf2dc02326ac6f84a2bd24376281337a502ea609c151f1d5ab6dc29ed24
+size 3595046