Upload RobertaForSequenceClassification

README.md

@@ -0,0 +1,42 @@
+---
+tags:
+- roberta
+- adapter-transformers
+datasets:
+- snli
+---
+
+# Adapter `varun-v-rao/roberta-large-bn-adapter-3.17M-snli-model2` for roberta-large
+
+An [adapter](https://adapterhub.ml) for the `roberta-large` model that was trained on the [snli](https://huggingface.co/datasets/snli/) 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("roberta-large")
+adapter_name = model.load_adapter("varun-v-rao/roberta-large-bn-adapter-3.17M-snli-model2", 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": 1024,
+  "model_class": "RobertaForSequenceClassification",
+  "model_name": "roberta-large",
+  "model_type": "roberta",
+  "name": "snli",
+  "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": "RobertaForSequenceClassification",
+  "model_name": "roberta-large",
+  "model_type": "roberta",
+  "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:b17d90542fc5b7489bbdcbcbb04ae3fa5ce4bded60ba5f53fa053a1850ab807d
+size 12722134

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499591b37b30f6665da07bc60b06f76d100d04d2c8f46d9ddd89dba3bdac0226
+size 4212840