Upload T5ForConditionalGeneration

README.md

@@ -0,0 +1,43 @@
+---
+tags:
+- adapter-transformers
+- t5
+datasets:
+- minh21/cpgQA-v1.0-unique-context-test-10-percent-validation-10-percent
+---
+
+# Adapter `legacy107/flan-t5-large-bottleneck-ia3-union-cpgQA` for google/flan-t5-large
+
+An [adapter](https://adapterhub.ml) for the `google/flan-t5-large` model that was trained on the [minh21/cpgQA-v1.0-unique-context-test-10-percent-validation-10-percent](https://huggingface.co/datasets/minh21/cpgQA-v1.0-unique-context-test-10-percent-validation-10-percent/) dataset.
+
+This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
+
+## Usage
+
+First, install `adapter-transformers`:
+
+```
+pip install -U adapter-transformers
+```
+_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
+
+Now, the adapter can be loaded and activated like this:
+
+```python
+from transformers import AutoAdapterModel
+
+model = AutoAdapterModel.from_pretrained("google/flan-t5-large")
+adapter_name = model.load_adapter("legacy107/flan-t5-large-bottleneck-ia3-union-cpgQA", 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 +1,61 @@
+{
+  "config": {
+    "architecture": "union",
+    "configs": [
+      {
+        "alpha": 1,
+        "architecture": "lora",
+        "attn_matrices": [
+          "q",
+          "v"
+        ],
+        "composition_mode": "scale",
+        "dropout": 0.0,
+        "init_weights": "ia3",
+        "intermediate_lora": true,
+        "output_lora": false,
+        "r": 1,
+        "selfattn_lora": 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": "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": true,
+        "non_linearity": "swish",
+        "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": 8,
+        "residual_before_ln": true,
+        "scaling": 1.0,
+        "shared_W_phm": false,
+        "shared_phm_rule": true,
+        "use_gating": false
+      }
+    ]
+  },
+  "hidden_size": 1024,
+  "model_class": "T5ForConditionalGeneration",
+  "model_name": "google/flan-t5-large",
+  "model_type": "t5",
+  "name": "question_answering_union",
+  "version": "3.2.1"
+}

head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 1024,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "T5ForConditionalGeneration",
+  "model_name": "google/flan-t5-large",
+  "model_type": "t5",
+  "name": null,
+  "num_labels": 2,
+  "version": "3.2.1"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aedb9c5c5598f396793e9d29e507713381f07bb78ca701dca68621f39749d39e
+size 102452625

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb5464bf1c6913a7a4b42eaceb34922625395282f520135121f9e769da254d5
+size 131597132