Add adapter gpt2_nli_rte_houlsby version 1

README.md

@@ -0,0 +1,54 @@
+---
+tags:
+- gpt2
+- adapterhub:nli/rte
+- adapter-transformers
+- text-classification
+license: "apache-2.0"
+---
+
+# Adapter `gpt2_nli_rte_houlsby` for gpt2
+
+Adapter for gpt2 in Houlsby architecture trained on the RTE dataset for 10 epochs with a learning rate of 1e-4.
+
+**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("gpt2")
+adapter_name = model.load_adapter("AdapterHub/gpt2_nli_rte_houlsby")
+model.set_active_adapters(adapter_name)
+```
+
+## Architecture & Training
+
+- Adapter architecture: houlsby
+- Prediction head: classification
+- Dataset: [RTE](https://aclweb.org/aclwiki/Recognizing_Textual_Entailment)
+
+## Author Information
+
+- Author name(s): Hannah Sterz
+- Author email: [email protected]
+- Author links: [Twitter](https://twitter.com/@h_sterz)
+
+
+
+## Citation
+
+```bibtex
+
+```
+
+*This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/gpt2_nli_rte_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": "GPT2AdapterModel",
+  "model_name": "gpt2",
+  "model_type": "gpt2",
+  "name": "rte",
+  "version": "0.2.0"
+}

head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": null,
+    "bias": false,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "entailment": 0,
+      "not_entailment": 1
+    },
+    "layers": 1,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "GPT2AdapterModel",
+  "model_name": "gpt2",
+  "model_type": "gpt2",
+  "name": "rte",
+  "version": "0.2.0"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93573a5fae1c00e5d0202174f821f6492f97c29ab16af84235bf4201e8128b9a
+size 7189718

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4cf718b4883231df8a40a9e1d284b1dee38e03ba6c06758152a9ef3195a7d2
+size 7443