WillHeld commited on
Commit
ae6a010
1 Parent(s): edf54c5
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - adapter-transformers
4
+ - roberta
5
+ datasets:
6
+ - glue
7
+ language:
8
+ - en
9
+ ---
10
+
11
+ # Adapter `WillHeld/pfadapter-roberta-base-qnli` for roberta-base
12
+
13
+ An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [glue](https://huggingface.co/datasets/glue/) 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 AutoAdapterModel
30
+
31
+ model = AutoAdapterModel.from_pretrained("roberta-base")
32
+ adapter_name = model.load_adapter("WillHeld/pfadapter-roberta-base-qnli", source="hf", set_active=True)
33
+ ```
34
+
35
+ ## Architecture & Training
36
+
37
+ <!-- Add some description here -->
38
+
39
+ ## Evaluation results
40
+
41
+ <!-- Add some description here -->
42
+
43
+ ## Citation
44
+
45
+ <!-- Add some description here -->
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": "relu",
18
+ "original_ln_after": true,
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": 16,
28
+ "residual_before_ln": true,
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": "RobertaAdapterModel",
36
+ "model_name": "roberta-base",
37
+ "model_type": "roberta",
38
+ "name": "qnli",
39
+ "version": "3.1.0"
40
+ }
head_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "activation_function": "tanh",
4
+ "bias": true,
5
+ "head_type": "classification",
6
+ "label2id": {
7
+ "entailment": 0,
8
+ "not_entailment": 1
9
+ },
10
+ "layers": 2,
11
+ "num_labels": 2,
12
+ "use_pooler": false
13
+ },
14
+ "hidden_size": 768,
15
+ "model_class": "RobertaAdapterModel",
16
+ "model_name": "roberta-base",
17
+ "model_type": "roberta",
18
+ "name": "qnli",
19
+ "version": "3.1.0"
20
+ }
pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caebe8b8c0ed60854b7cf83c20285d7232f3746d9924335823b7b0b4cc16511f
3
+ size 3595263
pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:070dd0069505444722bdf1a80cf9058f52ef6ba7f6dad15f61b6127ae366352e
3
+ size 2370171