Add adapter bert-base-uncased_sts_stackexchange_pfeiffer version cooking_stackexchange_com

README.md

@@ -0,0 +1,205 @@
+---
+tags:
+- bert
+- adapterhub:sts/stackexchange
+- adapter-transformers
+license: "apache-2.0"
+---
+
+# Adapter `bert-base-uncased_sts_stackexchange_pfeiffer` for bert-base-uncased
+
+Our adapters from the MultiCQA paper (https://arxiv.org/abs/2010.00980) trained on the different StackExchange forums (see "version") with self-supervised training signals of unlabeled questions.
+
+
+**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("bert-base-uncased")
+adapter_name = model.load_adapter("AdapterHub/bert-base-uncased_sts_stackexchange_pfeiffer")
+model.set_active_adapters(adapter_name)
+```
+
+## Architecture & Training
+
+- Adapter architecture: pfeiffer
+- Prediction head: None
+- Dataset: [StackExchange QA Similarity](https://arxiv.org/abs/2010.00980)
+
+## Author Information
+
+- Author name(s): Andreas Rücklé
+- Author email: rueckle@ukp.informatik.tu-darmstadt.de
+- Author links: [Website](http://rueckle.net), [GitHub](https://github.com/arueckle), [Twitter](https://twitter.com/arueckle)
+
+## Versions
+- `serverfault_com`
+- `mechanics_stackexchange_com`
+- `ux_stackexchange_com`
+- `history_stackexchange_com`
+- `judaism_stackexchange_com`
+- `workplace_stackexchange_com`
+- `freelancing_stackexchange_com`
+- `matheducators_stackexchange_com`
+- `literature_stackexchange_com`
+- `softwareengineering_stackexchange_com`
+- `patents_stackexchange_com`
+- `pets_stackexchange_com`
+- `softwarerecs_stackexchange_com`
+- `writers_stackexchange_com`
+- `gaming_stackexchange_com`
+- `movies_stackexchange_com`
+- `scifi_stackexchange_com`
+- `parenting_stackexchange_com`
+- `astronomy_stackexchange_com`
+- `bitcoin_stackexchange_com`
+- `rpg_stackexchange_com`
+- `fitness_stackexchange_com`
+- `cooking_stackexchange_com` **(main)**
+- `devops_stackexchange_com`
+- `avp_stackexchange_com`
+- `economics_stackexchange_com`
+- `health_stackexchange_com`
+- `sitecore_stackexchange_com`
+- `codegolf_stackexchange_com`
+- `askubuntu_com`
+- `sqa_stackexchange_com`
+- `ai_stackexchange_com`
+- `ell_stackexchange_com`
+- `tor_stackexchange_com`
+- `earthscience_stackexchange_com`
+- `worldbuilding_stackexchange_com`
+- `cstheory_stackexchange_com`
+- `gis_stackexchange_com`
+- `robotics_stackexchange_com`
+- `sustainability_stackexchange_com`
+- `mathematica_stackexchange_com`
+- `hardwarerecs_stackexchange_com`
+- `opensource_stackexchange_com`
+- `homebrew_stackexchange_com`
+- `diy_stackexchange_com`
+- `lifehacks_stackexchange_com`
+- `stats_stackexchange_com`
+- `hsm_stackexchange_com`
+- `christianity_stackexchange_com`
+- `boardgames_stackexchange_com`
+- `unix_stackexchange_com`
+- `space_stackexchange_com`
+- `android_stackexchange_com`
+- `quantumcomputing_stackexchange_com`
+- `windowsphone_stackexchange_com`
+- `music_stackexchange_com`
+- `cs_stackexchange_com`
+- `networkengineering_stackexchange_com`
+- `codereview_stackexchange_com`
+- `crypto_stackexchange_com`
+- `scicomp_stackexchange_com`
+- `math_stackexchange_com`
+- `anime_stackexchange_com`
+- `superuser_com`
+- `biology_stackexchange_com`
+- `photo_stackexchange_com`
+- `musicfans_stackexchange_com`
+- `genealogy_stackexchange_com`
+- `skeptics_stackexchange_com`
+- `gamedev_stackexchange_com`
+- `politics_stackexchange_com`
+- `expatriates_stackexchange_com`
+- `law_stackexchange_com`
+- `chemistry_stackexchange_com`
+- `blender_stackexchange_com`
+- `apple_stackexchange_com`
+- `dba_stackexchange_com`
+- `quant_stackexchange_com`
+- `elementaryos_stackexchange_com`
+- `travel_stackexchange_com`
+- `joomla_stackexchange_com`
+- `physics_stackexchange_com`
+- `interpersonal_stackexchange_com`
+- `pm_stackexchange_com`
+- `cogsci_stackexchange_com`
+- `bricks_stackexchange_com`
+- `ham_stackexchange_com`
+- `opendata_stackexchange_com`
+- `computergraphics_stackexchange_com`
+- `dsp_stackexchange_com`
+- `bicycles_stackexchange_com`
+- `drupal_stackexchange_com`
+- `philosophy_stackexchange_com`
+- `arduino_stackexchange_com`
+- `ethereum_stackexchange_com`
+- `emacs_stackexchange_com`
+- `woodworking_stackexchange_com`
+- `vi_stackexchange_com`
+- `sports_stackexchange_com`
+- `gardening_stackexchange_com`
+- `security_stackexchange_com`
+- `webapps_stackexchange_com`
+- `english_stackexchange_com`
+- `datascience_stackexchange_com`
+- `sharepoint_stackexchange_com`
+- `expressionengine_stackexchange_com`
+- `wordpress_stackexchange_com`
+- `stackoverflow_com`
+- `sound_stackexchange_com`
+- `webmasters_stackexchange_com`
+- `magento_stackexchange_com`
+- `bioinformatics_stackexchange_com`
+- `islam_stackexchange_com`
+- `raspberrypi_stackexchange_com`
+- `tex_stackexchange_com`
+- `chess_stackexchange_com`
+- `outdoors_stackexchange_com`
+- `retrocomputing_stackexchange_com`
+- `aviation_stackexchange_com`
+- `tridion_stackexchange_com`
+- `mythology_stackexchange_com`
+- `eosio_stackexchange_com`
+- `electronics_stackexchange_com`
+- `money_stackexchange_com`
+- `linguistics_stackexchange_com`
+- `stackapps_com`
+- `3dprinting_stackexchange_com`
+- `engineering_stackexchange_com`
+- `puzzling_stackexchange_com`
+- `academia_stackexchange_com`
+- `civicrm_stackexchange_com`
+- `martialarts_stackexchange_com`
+- `reverseengineering_stackexchange_com`
+- `hinduism_stackexchange_com`
+- `monero_stackexchange_com`
+- `hermeneutics_stackexchange_com`
+- `buddhism_stackexchange_com`
+- `craftcms_stackexchange_com`
+- `salesforce_stackexchange_com`
+- `poker_stackexchange_com`
+- `graphicdesign_stackexchange_com`
+
+## Citation
+
+```bibtex
+@inproceedings{rueckle-etal-2020-multicqa,
+  title = "{MultiCQA}: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale",
+  author = {R{\"u}ckl{\'e}, Andreas  and
+    Pfeiffer, Jonas and
+    Gurevych, Iryna},
+  booktitle = "Proceedings of The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP-2020)",
+  year = "2020",
+  address = "Virtual Conference",
+  url = "https://arxiv.org/abs/2010.00980",
+}
+
+```
+
+*This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/bert-base-uncased_sts_stackexchange_pfeiffer.yaml*.

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": "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": 12,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "bert-base-uncased",
+  "model_type": "bert",
+  "name": "cooking_stackexchange_com",
+  "version": "0.2.0"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9193ea08537c3cd33233e0fc3316b1a52800d8979cf90f5c201d48579f714ac0
+size 4776166

pytorch_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733b809d7effd1540811f0ef1c45b7c5b6d50e426ec4c0eeb7b6d7686dda5afe
+size 3562