Upload model

README.md

@@ -0,0 +1,40 @@
+---
+tags:
+- roberta
+- adapter-transformers
+---
+
+# Adapter `calpt/random_adapter_setup_test` for roberta-base
+
+An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the None dataset.
+
+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_setup("calpt/random_adapter_setup_test", set_active=True)
+```
+
+## Architecture & Training
+
+<!-- Add some description here -->
+
+## Evaluation results
+
+<!-- Add some description here -->
+
+## Citation
+
+<!-- Add some description here -->

a,b/adapter_fusion_config.json

@@ -0,0 +1,20 @@
+{
+  "config": {
+    "dropout_prob": null,
+    "key": true,
+    "query": true,
+    "query_before_ln": false,
+    "regularization": true,
+    "residual_before": false,
+    "temperature": false,
+    "value": true,
+    "value_before_softmax": true,
+    "value_initialized": true
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "a,b",
+  "version": "adapters.1.0.1"
+}

a,b/pytorch_model_adapter_fusion.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bcecfc2e75b242f8543b7c0ec1a62daa03fe188b4a55d5c4429f4a285e3ea2
+size 85030562

a/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "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,
+    "stochastic_depth": 0.0,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "a",
+  "version": "adapters.1.0.1"
+}

a/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79ecbb07db177ceaa80e80a5e47fe26826e2ef24a7c6bc5215e5700820807bd
+size 3594726

adapter_setup.json

@@ -0,0 +1,54 @@
+{
+  "adapter_setup": {
+    "type": "Stack",
+    "children": [
+      {
+        "type": "Fuse",
+        "children": [
+          {
+            "type": "single",
+            "children": [
+              "a"
+            ]
+          },
+          {
+            "type": "single",
+            "children": [
+              "b"
+            ]
+          }
+        ]
+      },
+      {
+        "type": "single",
+        "children": [
+          "c"
+        ]
+      }
+    ]
+  },
+  "head_setup": {
+    "type": "BatchSplit",
+    "children": [
+      {
+        "type": "single",
+        "children": [
+          "head_a"
+        ]
+      },
+      {
+        "type": "single",
+        "children": [
+          "head_b"
+        ]
+      }
+    ],
+    "kwargs": {
+      "batch_sizes": [
+        1,
+        1
+      ]
+    }
+  },
+  "version": "adapters.1.0.1"
+}

b/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "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,
+    "stochastic_depth": 0.0,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "b",
+  "version": "adapters.1.0.1"
+}

b/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59155aac6aa69c72d6fae6ae4cabc0c27ac3b1473f52c1023965042ae24521c1
+size 3594726

c/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "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,
+    "stochastic_depth": 0.0,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "c",
+  "version": "adapters.1.0.1"
+}

c/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae3b805ce309fc7cf7e833a3d50c8ab215439a6ca843aaa1e4931834df8608f
+size 3594726

head_a/head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "head_a",
+  "version": "adapters.1.0.1"
+}

head_a/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8516d68908fffa96a06f04777599c35d9db33f4d1e36b8b33e74172688232987
+size 2370600

head_b/head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "head_b",
+  "version": "adapters.1.0.1"
+}

head_b/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b709666017acdd1cdd922167f0fef1eafa2f933a27ae22169da43ffab988ae6
+size 2370600