model upload

README.md

@@ -0,0 +1,62 @@
+---
+inference: false
+tags:
+- onnx
+- question-answering
+- bert
+- adapterhub:qa/squad2
+- adapter-transformers
+datasets:
+- squad_v2
+language:
+- en
+---
+
+# ONNX export of Adapter `AdapterHub/bert-base-uncased-pf-squad_v2` for bert-base-uncased
+## Conversion of [AdapterHub/bert-base-uncased-pf-squad_v2](https://huggingface.co/AdapterHub/bert-base-uncased-pf-squad_v2) for UKP SQuARE
+
+
+## Usage
+```python
+onnx_path = hf_hub_download(repo_id='UKP-SQuARE/bert-base-uncased-pf-squad_v2-onnx', filename='model.onnx') # or model_quant.onnx for quantization
+onnx_model = InferenceSession(onnx_path, providers=['CPUExecutionProvider'])
+
+context = 'ONNX is an open format to represent models. The benefits of using ONNX include interoperability of frameworks and hardware optimization.'
+question = 'What are advantages of ONNX?'
+tokenizer = AutoTokenizer.from_pretrained('UKP-SQuARE/bert-base-uncased-pf-squad_v2-onnx')
+
+inputs = tokenizer(question, context, padding=True, truncation=True, return_tensors='np')
+inputs_int64 = {key: np.array(inputs[key], dtype=np.int64) for key in inputs}
+outputs = onnx_model.run(input_feed=dict(inputs_int64), output_names=None)
+```
+
+## 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-pre,
+    title = "{W}hat to Pre-Train on? {E}fficient Intermediate Task Selection",
+    author = {Poth, Clifton  and
+      Pfeiffer, Jonas  and
+      R{"u}ckl{'e}, Andreas  and
+      Gurevych, Iryna},
+    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
+    month = nov,
+    year = "2021",
+    address = "Online and Punta Cana, Dominican Republic",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2021.emnlp-main.827",
+    pages = "10585--10605",
+}
+```

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "adapters": {
+    "adapters": {
+      "squad_v2": "9076f36a74755ac4"
+    },
+    "config_map": {
+      "9076f36a74755ac4": {
+        "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
+      }
+    },
+    "fusion_config_map": {},
+    "fusions": {}
+  },
+  "architectures": [
+    "BertModelWithHeads"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "prediction_heads": {
+    "squad_v2": {
+      "activation_function": "tanh",
+      "head_type": "question_answering",
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layers": 1,
+      "num_labels": 2
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.3",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9945ea827365508fab468c67b88ece7248dd96535ee56cc6ad4eb6f55995e51
+size 439473675

model_quant.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea7f0fc981aef2c6ed759555b7b5b6ed7a499cff269fed23640838b738be85c
+size 110590829

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}