Add adapter roberta-base-sts_b_houlsby version 1

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- text-classification
+- adapter-transformers
+- roberta
+- adapterhub:sts/sts-b
+license: "apache-2.0"
+---
+
+# Adapter `roberta-base-sts_b_houlsby` for roberta-base
+
+STS-B adapter (with head) trained using the `run_glue.py` script with an extension that retains the best checkpoint (out of 30 epochs).
+
+
+**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-sts_b_houlsby")
+model.set_active_adapters(adapter_name)
+```
+
+## Architecture & Training
+
+- Adapter architecture: houlsby
+- Prediction head: classification
+- Dataset: [STS-B](http://ixa2.si.ehu.es/stswiki/index.php/STSbenchmark)
+
+## Author Information
+
+- Author name(s): Andreas Rücklé
+- Author email: rueckle@ukp.informatik.tu-darmstadt
+- Author links: [Website](http://rueckle.net), [GitHub](https://github.com/arueckle), [Twitter](https://twitter.com/@arueckle)
+
+
+
+## Citation
+
+```bibtex
+@article{pfeiffer2020AdapterHub,
+    title={AdapterHub: A Framework for Adapting Transformers},
+    author={Jonas Pfeiffer,
+            Andreas R\"uckl\'{e},
+            Clifton Poth,
+            Aishwarya Kamath,
+            Ivan Vuli\'{c},
+            Sebastian Ruder,
+            Kyunghyun Cho,
+            Iryna Gurevych},
+    journal={ArXiv},
+    year={2020}
+}
+
+```
+
+*This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/roberta-base-sts_b_houlsby.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": true,
+    "non_linearity": "swish",
+    "original_ln_after": true,
+    "original_ln_before": false,
+    "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": "sts-b",
+  "version": "0.2.0"
+}

head_config.json

@@ -0,0 +1,20 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0
+    },
+    "layers": 2,
+    "num_labels": 1,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "sts-b",
+  "version": "0.2.0"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631116e8f861367648e3ab25c5d9d36a770cd1120e16ac96e67aa438b4297263
+size 7190102

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531cf7623759c47c8e15c17ff90676bb9b06795a4e2e19353f6db4fc8b8e4f65
+size 2367528