Initial version.

README.md

@@ -0,0 +1,61 @@
+---
+tags:
+- roberta
+- adapterhub:semtag/pmb
+- adapter-transformers
+language:
+- en
+---
+
+# Adapter `AdapterHub/roberta-base-pf-pmb_sem_tagging` for roberta-base
+
+An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [semtag/pmb](https://adapterhub.ml/explore/semtag/pmb/) dataset and includes a prediction head for tagging.
+
+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 AutoModelWithHeads
+
+model = AutoModelWithHeads.from_pretrained("roberta-base")
+adapter_name = model.load_adapter("AdapterHub/roberta-base-pf-pmb_sem_tagging", source="hf")
+model.active_adapters = adapter_name
+```
+
+## Architecture & Training
+
+The training code for this adapter is available at https://github.com/adapter-hub/efficient-task-transfer.
+In particular, training configurations for all tasks can be found [here](https://github.com/adapter-hub/efficient-task-transfer/tree/master/run_configs).
+
+
+## Evaluation results
+
+Refer to [the paper](https://arxiv.org/pdf/2104.08247) for more information on results.
+
+## Citation
+
+If you use this adapter, please cite our paper ["What to Pre-Train on? Efficient Intermediate Task Selection"](https://arxiv.org/pdf/2104.08247):
+
+```bibtex
+@inproceedings{poth-etal-2021-what-to-pre-train-on,
+    title={What to Pre-Train on? Efficient Intermediate Task Selection},
+    author={Clifton Poth and Jonas Pfeiffer and Andreas Rücklé and Iryna Gurevych},
+    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
+    month = nov,
+    year = "2021",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/2104.08247",
+    pages = "to appear",
+}
+```

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "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,
+    "reduction_factor": 16,
+    "residual_before_ln": true
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaModelWithHeads",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "pmb_sem_tagging"
+}

head_config.json

@@ -0,0 +1,94 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "head_type": "tagging",
+    "label2id": {
+      "ALT": 0,
+      "AND": 1,
+      "APX": 2,
+      "ART": 3,
+      "BOT": 4,
+      "BUT": 5,
+      "CLO": 6,
+      "COL": 7,
+      "COM": 8,
+      "CON": 9,
+      "COO": 10,
+      "CTC": 11,
+      "DEC": 12,
+      "DEF": 13,
+      "DEG": 14,
+      "DIS": 15,
+      "DOM": 16,
+      "DOW": 17,
+      "DST": 18,
+      "DXP": 19,
+      "DXT": 20,
+      "EFS": 21,
+      "EMP": 22,
+      "ENS": 23,
+      "EPS": 24,
+      "EQU": 25,
+      "EVE": 26,
+      "EXG": 27,
+      "EXS": 28,
+      "EXT": 29,
+      "FUT": 30,
+      "GEO": 31,
+      "GPE": 32,
+      "GPO": 33,
+      "GRE": 34,
+      "GRP": 35,
+      "HAP": 36,
+      "HAS": 37,
+      "HES": 38,
+      "IMP": 39,
+      "INT": 40,
+      "IST": 41,
+      "ITJ": 42,
+      "LES": 43,
+      "LIT": 44,
+      "MOR": 45,
+      "MOY": 46,
+      "NAM": 47,
+      "NEC": 48,
+      "NIL": 49,
+      "NOT": 50,
+      "NOW": 51,
+      "NTH": 52,
+      "ORD": 53,
+      "ORG": 54,
+      "PER": 55,
+      "PFT": 56,
+      "POS": 57,
+      "PRG": 58,
+      "PRI": 59,
+      "PRO": 60,
+      "PRX": 61,
+      "PST": 62,
+      "QUC": 63,
+      "QUE": 64,
+      "QUV": 65,
+      "REF": 66,
+      "REL": 67,
+      "ROL": 68,
+      "SCO": 69,
+      "SST": 70,
+      "SUB": 71,
+      "TIM": 72,
+      "TNS": 73,
+      "TOP": 74,
+      "UNK": 75,
+      "UOM": 76,
+      "XCL": 77,
+      "YOC": 78
+    },
+    "layers": 1,
+    "num_labels": 79
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaModelWithHeads",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "pmb_sem_tagging"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e974eaa00e9ac273b4c9426f68ffad4000b2b7674945a27a6a5ac2f40bc1c4
+size 3595247

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2a4dd873dedcca12a9ae2f849d33409e3a6436817ead9a22f4a77c0987bcdc
+size 244087