jsl5710 commited on
Commit
533c981
1 Parent(s): f277eb7

Upload model

Browse files
README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - adapter-transformers
4
+ - bert
5
+ ---
6
+
7
+ # Adapter `jslai/MBERT_uncased_seq_bn_inv_HuberLoss_genetic_head_to_tail_20241129-073252` for google-bert/bert-base-multilingual-uncased
8
+
9
+ An [adapter](https://adapterhub.ml) for the `google-bert/bert-base-multilingual-uncased` model that was trained on the None dataset and includes a prediction head for classification.
10
+
11
+ This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
12
+
13
+ ## Usage
14
+
15
+ First, install `adapters`:
16
+
17
+ ```
18
+ pip install -U adapters
19
+ ```
20
+
21
+ Now, the adapter can be loaded and activated like this:
22
+
23
+ ```python
24
+ from adapters import AutoAdapterModel
25
+
26
+ model = AutoAdapterModel.from_pretrained("google-bert/bert-base-multilingual-uncased")
27
+ adapter_name = model.load_adapter("jslai/MBERT_uncased_seq_bn_inv_HuberLoss_genetic_head_to_tail_20241129-073252", set_active=True)
28
+ ```
29
+
30
+ ## Architecture & Training
31
+
32
+ <!-- Add some description here -->
33
+
34
+ ## Evaluation results
35
+
36
+ <!-- Add some description here -->
37
+
38
+ ## Citation
39
+
40
+ <!-- Add some description here -->
adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "dropout": 0.0,
6
+ "factorized_phm_W": true,
7
+ "factorized_phm_rule": false,
8
+ "hypercomplex_nonlinearity": "glorot-uniform",
9
+ "init_weights": "bert",
10
+ "inv_adapter": "nice",
11
+ "inv_adapter_reduction_factor": 2,
12
+ "is_parallel": false,
13
+ "learn_phm": true,
14
+ "leave_out": [],
15
+ "ln_after": false,
16
+ "ln_before": false,
17
+ "mh_adapter": false,
18
+ "non_linearity": "relu",
19
+ "original_ln_after": true,
20
+ "original_ln_before": true,
21
+ "output_adapter": true,
22
+ "phm_bias": true,
23
+ "phm_c_init": "normal",
24
+ "phm_dim": 4,
25
+ "phm_init_range": 0.0001,
26
+ "phm_layer": false,
27
+ "phm_rank": 1,
28
+ "reduction_factor": 16,
29
+ "residual_before_ln": true,
30
+ "scaling": 1.0,
31
+ "shared_W_phm": false,
32
+ "shared_phm_rule": true,
33
+ "use_gating": false
34
+ },
35
+ "hidden_size": 768,
36
+ "model_class": "BertAdapterModel",
37
+ "model_name": "google-bert/bert-base-multilingual-uncased",
38
+ "model_type": "bert",
39
+ "name": "MBERT_uncased_seq_bn_inv",
40
+ "version": "adapters.1.0.1"
41
+ }
head_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "activation_function": "tanh",
4
+ "bias": true,
5
+ "dropout_prob": null,
6
+ "head_type": "classification",
7
+ "label2id": {
8
+ "False": 0,
9
+ "True": 1
10
+ },
11
+ "layers": 2,
12
+ "num_labels": 2,
13
+ "use_pooler": false
14
+ },
15
+ "hidden_size": 768,
16
+ "model_class": "BertAdapterModel",
17
+ "model_name": "google-bert/bert-base-multilingual-uncased",
18
+ "model_type": "bert",
19
+ "name": "MBERT_uncased_seq_bn_inv",
20
+ "version": "adapters.1.0.1"
21
+ }
pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e00213188885dbf7949210fa93a97dc773837fb1735cbd8cd9fe20a033af4071
3
+ size 4783438
pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b0ade5334c259c0b0ae6a20c5259da98dcc45bbfaa2520c68533d51333ffb9
3
+ size 2370728