calpt commited on
Commit
0071bf6
1 Parent(s): ebe7644

Upload model

Browse files
Files changed (3) hide show
  1. README.md +66 -0
  2. adapter_config.json +40 -0
  3. pytorch_adapter.bin +3 -0
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - xmod
4
+ - adapters
5
+ - adapterhub:he/cc100
6
+ language:
7
+ - he
8
+ license: "mit"
9
+ ---
10
+
11
+ # Adapter `AdapterHub/xmod-base-he_IL` for AdapterHub/xmod-base
12
+
13
+ An [adapter](https://adapterhub.ml) for the `AdapterHub/xmod-base` model that was trained on the [he/cc100](https://adapterhub.ml/explore/he/cc100/) dataset.
14
+
15
+ This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
16
+
17
+ ## Usage
18
+
19
+ First, install `adapters`:
20
+
21
+ ```
22
+ pip install -U adapters
23
+ ```
24
+
25
+ Now, the adapter can be loaded and activated like this:
26
+
27
+ ```python
28
+ from adapters import AutoAdapterModel
29
+
30
+ model = AutoAdapterModel.from_pretrained("AdapterHub/xmod-base")
31
+ adapter_name = model.load_adapter("AdapterHub/xmod-base-he_IL", source="hf", set_active=True)
32
+ ```
33
+
34
+ ## Architecture & Training
35
+
36
+ This adapter was extracted from the original model checkpoint [facebook/xmod-base](https://huggingface.co/facebook/xmod-base) to allow loading it independently via the Adapters library.
37
+ For more information on architecture and training, please refer to the original model card.
38
+
39
+ ## Evaluation results
40
+
41
+ <!-- Add some description here -->
42
+
43
+ ## Citation
44
+
45
+ [Lifting the Curse of Multilinguality by Pre-training Modular Transformers (Pfeiffer et al., 2022)](http://dx.doi.org/10.18653/v1/2022.naacl-main.255)
46
+
47
+ ```
48
+ @inproceedings{pfeiffer-etal-2022-lifting,
49
+ title = "Lifting the Curse of Multilinguality by Pre-training Modular Transformers",
50
+ author = "Pfeiffer, Jonas and
51
+ Goyal, Naman and
52
+ Lin, Xi and
53
+ Li, Xian and
54
+ Cross, James and
55
+ Riedel, Sebastian and
56
+ Artetxe, Mikel",
57
+ booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
58
+ month = jul,
59
+ year = "2022",
60
+ address = "Seattle, United States",
61
+ publisher = "Association for Computational Linguistics",
62
+ url = "https://aclanthology.org/2022.naacl-main.255",
63
+ doi = "10.18653/v1/2022.naacl-main.255",
64
+ pages = "3479--3495"
65
+ }
66
+ ```
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "factorized_phm_W": true,
6
+ "factorized_phm_rule": false,
7
+ "hypercomplex_nonlinearity": "glorot-uniform",
8
+ "init_weights": "bert",
9
+ "inv_adapter": null,
10
+ "inv_adapter_reduction_factor": null,
11
+ "is_parallel": false,
12
+ "learn_phm": true,
13
+ "leave_out": [],
14
+ "ln_after": false,
15
+ "ln_before": false,
16
+ "mh_adapter": false,
17
+ "non_linearity": "gelu",
18
+ "original_ln_after": false,
19
+ "original_ln_before": true,
20
+ "output_adapter": true,
21
+ "phm_bias": true,
22
+ "phm_c_init": "normal",
23
+ "phm_dim": 4,
24
+ "phm_init_range": 0.0001,
25
+ "phm_layer": false,
26
+ "phm_rank": 1,
27
+ "reduction_factor": 2,
28
+ "residual_before_ln": false,
29
+ "scaling": 1.0,
30
+ "shared_W_phm": false,
31
+ "shared_phm_rule": true,
32
+ "use_gating": false
33
+ },
34
+ "hidden_size": 768,
35
+ "model_class": "XmodAdapterModel",
36
+ "model_name": "AdapterHub/xmod-base",
37
+ "model_type": "xmod",
38
+ "name": "he_IL",
39
+ "version": "0.0.0"
40
+ }
pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94aca013a48e5d348ce5a74f7b418f2e8f8c9c917561e3fbf60b269d3376f0f
3
+ size 28383333