Upload MT5ForConditionalGeneration

README.md

@@ -1,3 +1,42 @@
----
-license: gpl-3.0
----
+---
+tags:
+- mt5
+- adapter-transformers
+datasets:
+- jfeil/GermanDefinitionGeneration-Distillation
+---
+
+# Adapter `jfeil/GermanDefinitionGeneration-Distillation` for google/mt5-base
+
+An [adapter](https://adapterhub.ml) for the `google/mt5-base` model that was trained on the [jfeil/GermanDefinitionGeneration-Distillation](https://huggingface.co/datasets/jfeil/GermanDefinitionGeneration-Distillation/) 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("google/mt5-base")
+adapter_name = model.load_adapter("jfeil/GermanDefinitionGeneration-Distillation", 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 +1,41 @@
+{
+  "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": "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": 4.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "MT5ForConditionalGeneration",
+  "model_name": "google/mt5-base",
+  "model_type": "mt5",
+  "name": "definition_base",
+  "version": "adapters.1.0.0.dev0"
+}

head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 768,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "MT5ForConditionalGeneration",
+  "model_name": "google/mt5-base",
+  "model_type": "mt5",
+  "name": null,
+  "num_labels": 2,
+  "version": "adapters.1.0.0.dev0"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f64058017443de57b65f3a7e6eb66b6ff224b988ca6407e8fc93bb573884ec
+size 56768982

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31898c8036e99e7d00bafbca63b85f1a8ce7ee95bbfb591c5681d33d562e879
+size 768308499