Upload MBartForConditionalGeneration

README.md

@@ -0,0 +1,43 @@
+---
+tags:
+- adapter-transformers
+- adapterhub:summarization/hiru_structured_5100_first3
+- mbart
+datasets:
+- hiru_structutred_5100_first3
+---
+
+# Adapter `Pubudu/mbart-large-cc25_prefix_tuning_12_par_bn_rf_4_hiru_structured_first3` for facebook/mbart-large-cc25
+
+An [adapter](https://adapterhub.ml) for the `facebook/mbart-large-cc25` model that was trained on the [summarization/hiru_structured_5100_first3](https://adapterhub.ml/explore/summarization/hiru_structured_5100_first3/) 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-cc25")
+adapter_name = model.load_adapter("Pubudu/mbart-large-cc25_prefix_tuning_12_par_bn_rf_4_hiru_structured_first3", 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 +1,58 @@
+{
+  "config": {
+    "architecture": "union",
+    "configs": [
+      {
+        "architecture": "prefix_tuning",
+        "bottleneck_size": 800,
+        "cross_prefix": true,
+        "dropout": 0.0,
+        "encoder_prefix": true,
+        "flat": false,
+        "leave_out": [],
+        "non_linearity": "tanh",
+        "prefix_length": 12,
+        "shared_gating": true,
+        "use_gating": false
+      },
+      {
+        "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": 4,
+        "residual_before_ln": true,
+        "scaling": 4.0,
+        "shared_W_phm": false,
+        "shared_phm_rule": true,
+        "use_gating": false
+      }
+    ]
+  },
+  "hidden_size": 1024,
+  "model_class": "MBartForConditionalGeneration",
+  "model_name": "facebook/mbart-large-cc25",
+  "model_type": "mbart",
+  "name": "mbart-large-cc25_prefix_tuning_12_par_bn_rf_4_hiru_structured_first3",
+  "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-cc25",
+  "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 sha256:97191af8ec4d40fea939d2a682d8069fd1cc5882ac3a629196be1e1e35a0c731
+size 296855468

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d847a7c53a8cf4cbf1435e76e4bd7db89bde724cc5aaa97a7111e858f6d02a
+size 1025116314