Upload model

README.md

@@ -0,0 +1,42 @@
+---
+tags:
+- roberta
+- adapter-transformers
+datasets:
+- BigTMiami/amazon_split_25M_reviews_20_percent_condensed
+---
+
+# Adapter `BigTMiami/A1_adapter_seq_bn_pretrain_P_5` for roberta-base
+
+An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_split_25M_reviews_20_percent_condensed](https://huggingface.co/datasets/BigTMiami/amazon_split_25M_reviews_20_percent_condensed/) dataset and includes a prediction head for masked lm.
+
+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("BigTMiami/A1_adapter_seq_bn_pretrain_P_5", 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": "A1_adapter_seq_bn_pretrain_P_5",
+  "version": "0.1.2"
+}

head_config.json

@@ -0,0 +1,19 @@
+{
+  "config": {
+    "activation_function": "gelu",
+    "bias": true,
+    "embedding_size": 768,
+    "head_type": "masked_lm",
+    "label2id": null,
+    "layer_norm": true,
+    "layers": 2,
+    "shift_labels": false,
+    "vocab_size": 50265
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "A1_adapter_seq_bn_pretrain_P_5",
+  "version": "0.1.2"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee2c2a85bfaf415df8f4403f31a540a6aee035e4552cc2e36051dd3d72230ee
+size 3596774

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4ca96ef94eca8d953bb0569693ec268a38e1b09d4e6dc36c2ce7f66de98310
+size 156986486