Downloads · 30 days
2
18% of all-time downloads
gpt2_sts_sts-b_houlsby
AdapterHub/gpt2_sts_sts-b_houlsby
gpt2_sts_sts-b_houlsby is a text classification model from AdapterHub. Use it when you need a label for a piece of text. It is set up for adapter-transformers. The card lists the license as apache-2.0.
Adapter for gpt2 in Houlsby architecture trained on the STS-B dataset for 10 epochs with a learning rate of 1e-4.
All-time downloads
11
Public
Repo size
7.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin7.2 MB · 100%
At a glance
- Task
- Text Classification
- Library
- adapter-transformers
- License
- apache-2.0
- Access
- Public
- Created
- May 5, 2024
- Updated
- May 5, 2024
- SHA
- 1af59be9
Try a prompt
Model card
From the Hugging Face model README
Adapter gpt2_sts_sts-b_houlsby for gpt2
Adapter for gpt2 in Houlsby architecture trained on the STS-B dataset for 10 epochs with a learning rate of 1e-4.
This adapter was created for usage with the Adapters library.
Usage
First, install adapters:
pip install -U adapters
Now, the adapter can be loaded and activated like this:
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("gpt2")
adapter_name = model.load_adapter("AdapterHub/gpt2_sts_sts-b_houlsby")
model.set_active_adapters(adapter_name)
Architecture & Training
- Adapter architecture: houlsby
- Prediction head: classification
- Dataset: STS-B
Author Information
- Author name(s): Hannah Sterz
- Author email: [email protected]
- Author links: Twitter
Citation
This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/gpt2_sts_sts-b_houlsby.yaml.
- Task
- Text Classification
- Library
- adapter-transformers
- License
- apache-2.0
- Created
- May 5, 2024
- Updated
- May 5, 2024