Commit
•
dd92392
1
Parent(s):
16917d6
Upload GPT2ForQuestionAnswering
Browse files- README.md +42 -0
- adapter_config.json +40 -0
- head_config.json +14 -0
- pytorch_adapter.bin +3 -0
- pytorch_model_head.bin +3 -0
README.md
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- adapter-transformers
|
4 |
+
- gpt2
|
5 |
+
datasets:
|
6 |
+
- squad
|
7 |
+
---
|
8 |
+
|
9 |
+
# Adapter `varun-v-rao/gpt2-large-bn-adapter-7.42M-squad-model3` for openai-community/gpt2-large
|
10 |
+
|
11 |
+
An [adapter](https://adapterhub.ml) for the `openai-community/gpt2-large` model that was trained on the [squad](https://huggingface.co/datasets/squad/) dataset.
|
12 |
+
|
13 |
+
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
|
14 |
+
|
15 |
+
## Usage
|
16 |
+
|
17 |
+
First, install `adapters`:
|
18 |
+
|
19 |
+
```
|
20 |
+
pip install -U adapters
|
21 |
+
```
|
22 |
+
|
23 |
+
Now, the adapter can be loaded and activated like this:
|
24 |
+
|
25 |
+
```python
|
26 |
+
from adapters import AutoAdapterModel
|
27 |
+
|
28 |
+
model = AutoAdapterModel.from_pretrained("openai-community/gpt2-large")
|
29 |
+
adapter_name = model.load_adapter("varun-v-rao/gpt2-large-bn-adapter-7.42M-squad-model3", source="hf", set_active=True)
|
30 |
+
```
|
31 |
+
|
32 |
+
## Architecture & Training
|
33 |
+
|
34 |
+
<!-- Add some description here -->
|
35 |
+
|
36 |
+
## Evaluation results
|
37 |
+
|
38 |
+
<!-- Add some description here -->
|
39 |
+
|
40 |
+
## Citation
|
41 |
+
|
42 |
+
<!-- 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": 1280,
|
35 |
+
"model_class": "GPT2ForQuestionAnswering",
|
36 |
+
"model_name": "openai-community/gpt2-large",
|
37 |
+
"model_type": "gpt2",
|
38 |
+
"name": "squad",
|
39 |
+
"version": "0.1.1"
|
40 |
+
}
|
head_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": null,
|
3 |
+
"hidden_size": 1280,
|
4 |
+
"label2id": {
|
5 |
+
"LABEL_0": 0,
|
6 |
+
"LABEL_1": 1
|
7 |
+
},
|
8 |
+
"model_class": "GPT2ForQuestionAnswering",
|
9 |
+
"model_name": "openai-community/gpt2-large",
|
10 |
+
"model_type": "gpt2",
|
11 |
+
"name": null,
|
12 |
+
"num_labels": 2,
|
13 |
+
"version": "0.1.1"
|
14 |
+
}
|
pytorch_adapter.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d7f9854ed0f9e000daa6a9890c85d0cbbd6bb26420a759a13dd222d4c6978e5
|
3 |
+
size 29739506
|
pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06a5b204393a92825d730a39e409dcd1feb9db6c9dfdf9e3fa47fccef7093889
|
3 |
+
size 11802
|