add model

README.md

@@ -0,0 +1,45 @@
+---
+tags:
+- adapter-transformers
+- roberta
+datasets:
+- glue
+language:
+- en
+---
+
+# Adapter `WillHeld/pfadapter-roberta-base-stsb` for roberta-base
+
+An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [glue](https://huggingface.co/datasets/glue/) dataset and includes a prediction head for classification.
+
+This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
+
+## Usage
+
+First, install `adapter-transformers`:
+
+```
+pip install -U adapter-transformers
+```
+_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)_
+
+Now, the adapter can be loaded and activated like this:
+
+```python
+from transformers import AutoAdapterModel
+
+model = AutoAdapterModel.from_pretrained("roberta-base")
+adapter_name = model.load_adapter("WillHeld/pfadapter-roberta-base-stsb", source="hf", set_active=True)
+```
+
+## Architecture & Training
+
+<!-- Add some description here -->
+
+## Evaluation results
+
+<!-- Add some description here -->
+
+## Citation
+
+<!-- Add some description here -->

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "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": "stsb",
+  "version": "3.1.0"
+}

head_config.json

@@ -0,0 +1,19 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "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": "stsb",
+  "version": "3.1.0"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e00b90eac95a3ea9e34335bf3327a787d17d4a7483de0edd47df1390137c27
+size 3595267

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3048edac16eb19db27206a1af984dccf9fa55814b3dd7b1a17074ffdc3ae55d
+size 2367103