Downloads · 30 days
13
0% of all-time downloads
dyda-deberta-pair
diwank/dyda-deberta-pair
dyda-deberta-pair is a text classification model from diwank. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
Deberta-based Daily Dialog style dialog-act annotations classification model. It takes two sentences as inputs (one previous and one current of a dialog). The previous sentence can be an empty string if this is the fi…
All-time downloads
2.9K
Public
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.1 GB · 50%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- deberta
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Feb 2, 2022
- SHA
- dd61dd9a
Try a prompt
Model card
From the Hugging Face model README
diwank/dyda-deberta-pair
Deberta-based Daily Dialog style dialog-act annotations classification model. It takes two sentences as inputs (one previous and one current of a dialog). The previous sentence can be an empty string if this is the first utterance of a speaker in a dialog. Outputs one of four labels (exactly as in the daily-dialog dataset ): dummy (0), inform (1), question (2), directive (3), commissive (4)
Usage
from simpletransformers.classification import (
ClassificationModel, ClassificationArgs
)
model = ClassificationModel("deberta", "diwank/dyda-deberta-pair")
convert_to_label = lambda n: ["__dummy__ (0), inform (1), question (2), directive (3), commissive (4)".split(', ')[i] for i in n]
predictions, raw_outputs = model.predict([["Say what is the meaning of life?", "I dont know"]])
convert_to_label(predictions) # inform (1)
- Task
- Text Classification
- Library
- transformers
- Type
- deberta
- License
- mit
- Created
- Mar 2, 2022
- Updated
- Feb 2, 2022