calpt commited on
Commit
0da043f
1 Parent(s): 0f43608

Initial version.

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - roberta
4
+ - adapterhub:pos/conll2003
5
+ - adapter-transformers
6
+ datasets:
7
+ - conll2003
8
+ language:
9
+ - en
10
+ ---
11
+
12
+ # Adapter `AdapterHub/roberta-base-pf-conll2003_pos` for roberta-base
13
+
14
+ An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [pos/conll2003](https://adapterhub.ml/explore/pos/conll2003/) dataset and includes a prediction head for tagging.
15
+
16
+ This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
17
+
18
+ ## Usage
19
+
20
+ First, install `adapter-transformers`:
21
+
22
+ ```
23
+ pip install -U adapter-transformers
24
+ ```
25
+ _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)_
26
+
27
+ Now, the adapter can be loaded and activated like this:
28
+
29
+ ```python
30
+ from transformers import AutoModelWithHeads
31
+
32
+ model = AutoModelWithHeads.from_pretrained("roberta-base")
33
+ adapter_name = model.load_adapter("AdapterHub/roberta-base-pf-conll2003_pos", source="hf")
34
+ model.active_adapters = adapter_name
35
+ ```
36
+
37
+ ## Architecture & Training
38
+
39
+ The training code for this adapter is available at https://github.com/adapter-hub/efficient-task-transfer.
40
+ In particular, training configurations for all tasks can be found [here](https://github.com/adapter-hub/efficient-task-transfer/tree/master/run_configs).
41
+
42
+
43
+ ## Evaluation results
44
+
45
+ Refer to [the paper](https://arxiv.org/pdf/2104.08247) for more information on results.
46
+
47
+ ## Citation
48
+
49
+ If you use this adapter, please cite our paper ["What to Pre-Train on? Efficient Intermediate Task Selection"](https://arxiv.org/pdf/2104.08247):
50
+
51
+ ```bibtex
52
+ @inproceedings{poth-etal-2021-what-to-pre-train-on,
53
+ title={What to Pre-Train on? Efficient Intermediate Task Selection},
54
+ author={Clifton Poth and Jonas Pfeiffer and Andreas Rücklé and Iryna Gurevych},
55
+ booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
56
+ month = nov,
57
+ year = "2021",
58
+ address = "Online",
59
+ publisher = "Association for Computational Linguistics",
60
+ url = "https://arxiv.org/abs/2104.08247",
61
+ pages = "to appear",
62
+ }
63
+ ```
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": "RobertaModelWithHeads",
20
+ "model_name": "roberta-base",
21
+ "model_type": "roberta",
22
+ "name": "conll2003_pos"
23
+ }
head_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "activation_function": "tanh",
4
+ "head_type": "tagging",
5
+ "label2id": {
6
+ "\"": 0,
7
+ "#": 2,
8
+ "$": 3,
9
+ "''": 1,
10
+ "(": 4,
11
+ ")": 5,
12
+ ",": 6,
13
+ ".": 7,
14
+ ":": 8,
15
+ "CC": 10,
16
+ "CD": 11,
17
+ "DT": 12,
18
+ "EX": 13,
19
+ "FW": 14,
20
+ "IN": 15,
21
+ "JJ": 16,
22
+ "JJR": 17,
23
+ "JJS": 18,
24
+ "LS": 19,
25
+ "MD": 20,
26
+ "NN": 21,
27
+ "NNP": 22,
28
+ "NNPS": 23,
29
+ "NNS": 24,
30
+ "NN|SYM": 25,
31
+ "PDT": 26,
32
+ "POS": 27,
33
+ "PRP": 28,
34
+ "PRP$": 29,
35
+ "RB": 30,
36
+ "RBR": 31,
37
+ "RBS": 32,
38
+ "RP": 33,
39
+ "SYM": 34,
40
+ "TO": 35,
41
+ "UH": 36,
42
+ "VB": 37,
43
+ "VBD": 38,
44
+ "VBG": 39,
45
+ "VBN": 40,
46
+ "VBP": 41,
47
+ "VBZ": 42,
48
+ "WDT": 43,
49
+ "WP": 44,
50
+ "WP$": 45,
51
+ "WRB": 46,
52
+ "``": 9
53
+ },
54
+ "layers": 1,
55
+ "num_labels": 47
56
+ },
57
+ "hidden_size": 768,
58
+ "model_class": "RobertaModelWithHeads",
59
+ "model_name": "roberta-base",
60
+ "model_type": "roberta",
61
+ "name": "conll2003_pos"
62
+ }
pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f9a68f25524e3a469f16e18f96dc26b281d3a9c70e4c83dd55aac9f7f6b78a
3
+ size 3595119
pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b047fd4721aaf5c79a12a7431ee6fbfea82565b2880f6202320c06bf746ce11
3
+ size 145591