Upload MBartForConditionalGeneration

README.md

@@ -0,0 +1,43 @@
+---
+tags:
+- adapterhub:summarization/dinamina_5400_full_text
+- mbart
+- adapter-transformers
+datasets:
+- dinamina_5400_full_text
+---
+
+# Adapter `Pubudu/mbart-large-50_scaled_par_bn_rf_16_dinamina_5400` for facebook/mbart-large-50
+
+An [adapter](https://adapterhub.ml) for the `facebook/mbart-large-50` model that was trained on the [summarization/dinamina_5400_full_text](https://adapterhub.ml/explore/summarization/dinamina_5400_full_text/) 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("facebook/mbart-large-50")
+adapter_name = model.load_adapter("Pubudu/mbart-large-50_scaled_par_bn_rf_16_dinamina_5400", 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": "mam_adapter",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": true,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "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": 2,
+    "residual_before_ln": true,
+    "scaling": "learned",
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "hidden_size": 1024,
+  "model_class": "MBartForConditionalGeneration",
+  "model_name": "facebook/mbart-large-50",
+  "model_type": "mbart",
+  "name": "mbart-large-50_scaled_par_bn_rf_16_dinamina_5400",
+  "version": "0.1.1"
+}

head_config.json

@@ -0,0 +1,15 @@
+{
+  "config": null,
+  "hidden_size": 1024,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "model_class": "MBartForConditionalGeneration",
+  "model_name": "facebook/mbart-large-50",
+  "model_type": "mbart",
+  "name": null,
+  "num_labels": 3,
+  "version": "0.1.1"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddafa853cdc057a7f33558db6851d708f9152b6d6e33a960e64d70c4002cad2f
+size 100860194

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adcc43a196d39e07adb0d2ce5a89621565caf0187b28c81222c9bb08b8fa37f7
+size 1025227034