Upload model

README.md

@@ -0,0 +1,43 @@
+---
+tags:
+- adapter-transformers
+- xlm-roberta
+- adapterhub:fill-mask/wikipedia-amharic
+datasets:
+- wikipedia
+---
+
+# Adapter `solwol/xml-roberta-amharic` for xlm-roberta-base
+
+An [adapter](https://adapterhub.ml) for the `xlm-roberta-base` model that was trained on the [fill-mask/wikipedia-amharic](https://adapterhub.ml/explore/fill-mask/wikipedia-amharic/) 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("xlm-roberta-base")
+adapter_name = model.load_adapter("solwol/xml-roberta-amharic", 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": "XLMRobertaAdapterModel",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "name": "amharic-wiki",
+  "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": 250002
+  },
+  "hidden_size": 768,
+  "model_class": "XLMRobertaAdapterModel",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "name": "amharic-wiki",
+  "version": "0.1.2"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9240986c3c0e72fedf932394d0a324e78c589e2dd7f824fbbb23aa66f36c1bba
+size 3595942

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206c015e77a027a055ad4fadc17d41e93834541133eb79ef5e42c996845a00ed
+size 771377398