calpt commited on
Commit
41ad0fd
1 Parent(s): 9142fa0

Initial version.

Browse files

README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - bert
4
+ - adapter-transformers
5
+ datasets:
6
+ - trec
7
+ language:
8
+ - en
9
+ ---
10
+
11
+ # Adapter `AdapterHub/bert-base-uncased-pf-trec` for bert-base-uncased
12
+
13
+ An [adapter](https://adapterhub.ml) for the `bert-base-uncased` model that was trained on the [trec](https://huggingface.co/datasets/trec/) dataset and includes a prediction head for classification.
14
+
15
+ This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
16
+
17
+ ## Usage
18
+
19
+ First, install `adapter-transformers`:
20
+
21
+ ```
22
+ pip install -U adapter-transformers
23
+ ```
24
+ _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)_
25
+
26
+ Now, the adapter can be loaded and activated like this:
27
+
28
+ ```python
29
+ from transformers import AutoModelWithHeads
30
+
31
+ model = AutoModelWithHeads.from_pretrained("bert-base-uncased")
32
+ adapter_name = model.load_adapter("AdapterHub/bert-base-uncased-pf-trec", source="hf")
33
+ model.active_adapters = adapter_name
34
+ ```
35
+
36
+ ## Architecture & Training
37
+
38
+ The training code for this adapter is available at https://github.com/adapter-hub/efficient-task-transfer.
39
+ In particular, training configurations for all tasks can be found [here](https://github.com/adapter-hub/efficient-task-transfer/tree/master/run_configs).
40
+
41
+
42
+ ## Evaluation results
43
+
44
+ Refer to [the paper](https://arxiv.org/pdf/2104.08247) for more information on results.
45
+
46
+ ## Citation
47
+
48
+ If you use this adapter, please cite our paper ["What to Pre-Train on? Efficient Intermediate Task Selection"](https://arxiv.org/pdf/2104.08247):
49
+
50
+ ```bibtex
51
+ @inproceedings{poth-etal-2021-what-to-pre-train-on,
52
+ title={What to Pre-Train on? Efficient Intermediate Task Selection},
53
+ author={Clifton Poth and Jonas Pfeiffer and Andreas Rücklé and Iryna Gurevych},
54
+ booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
55
+ month = nov,
56
+ year = "2021",
57
+ address = "Online",
58
+ publisher = "Association for Computational Linguistics",
59
+ url = "https://arxiv.org/abs/2104.08247",
60
+ pages = "to appear",
61
+ }
62
+ ```
adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "inv_adapter": null,
6
+ "inv_adapter_reduction_factor": null,
7
+ "leave_out": [],
8
+ "ln_after": false,
9
+ "ln_before": false,
10
+ "mh_adapter": false,
11
+ "non_linearity": "relu",
12
+ "original_ln_after": true,
13
+ "original_ln_before": true,
14
+ "output_adapter": true,
15
+ "reduction_factor": 16,
16
+ "residual_before_ln": true
17
+ },
18
+ "hidden_size": 768,
19
+ "model_class": "BertModelWithHeads",
20
+ "model_name": "bert-base-uncased",
21
+ "model_type": "bert",
22
+ "name": "trec"
23
+ }
head_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "activation_function": "tanh",
4
+ "bias": true,
5
+ "head_type": "classification",
6
+ "label2id": {
7
+ "LABEL_0": 0,
8
+ "LABEL_1": 1,
9
+ "LABEL_2": 2,
10
+ "LABEL_3": 3,
11
+ "LABEL_4": 4,
12
+ "LABEL_5": 5
13
+ },
14
+ "layers": 2,
15
+ "num_labels": 6,
16
+ "use_pooler": false
17
+ },
18
+ "hidden_size": 768,
19
+ "model_class": "BertModelWithHeads",
20
+ "model_name": "bert-base-uncased",
21
+ "model_type": "bert",
22
+ "name": "trec"
23
+ }
pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e7665d44f52a020ed4fb3a4d98d5b699a236427d95238b60ad626e3517f8ca
3
+ size 3594543
pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8e8354785f275ccaa1249026c3035ae9f5a624757f5a35c2c1f001af64c1a0
3
+ size 2382463