add model
Browse files- README.md +45 -0
- adapter_config.json +40 -0
- head_config.json +21 -0
- pytorch_adapter.bin +3 -0
- pytorch_model_head.bin +3 -0
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- bert
|
4 |
+
- adapter-transformers
|
5 |
+
datasets:
|
6 |
+
- glue
|
7 |
+
language:
|
8 |
+
- en
|
9 |
+
---
|
10 |
+
|
11 |
+
# Adapter `SALT-NLP/pfadapter-bert-base-uncased-mnli-combined-value` for bert-base-uncased
|
12 |
+
|
13 |
+
An [adapter](https://adapterhub.ml) for the `bert-base-uncased` 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("bert-base-uncased")
|
32 |
+
adapter_name = model.load_adapter("SALT-NLP/pfadapter-bert-base-uncased-mnli-combined-value", 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": "BertAdapterModel",
|
36 |
+
"model_name": "bert-base-uncased",
|
37 |
+
"model_type": "bert",
|
38 |
+
"name": "mnli",
|
39 |
+
"version": "3.1.0"
|
40 |
+
}
|
head_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"activation_function": "tanh",
|
4 |
+
"bias": true,
|
5 |
+
"head_type": "classification",
|
6 |
+
"label2id": {
|
7 |
+
"contradiction": 2,
|
8 |
+
"entailment": 0,
|
9 |
+
"neutral": 1
|
10 |
+
},
|
11 |
+
"layers": 2,
|
12 |
+
"num_labels": 3,
|
13 |
+
"use_pooler": false
|
14 |
+
},
|
15 |
+
"hidden_size": 768,
|
16 |
+
"model_class": "BertAdapterModel",
|
17 |
+
"model_name": "bert-base-uncased",
|
18 |
+
"model_type": "bert",
|
19 |
+
"name": "mnli",
|
20 |
+
"version": "3.1.0"
|
21 |
+
}
|
pytorch_adapter.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e84c9f405f8e9bcf450deb92c95e6153c70a99886512cde1ca9e8781435f811
|
3 |
+
size 3595162
|
pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9ba7e6cc5837611d920e7ba6c921b335f0c8d3a76e38367874f53039340c119
|
3 |
+
size 2373243
|