Downloads · 30 days
13
0% of all-time downloads
DeBERTa-v3-FaithAug
juliussteen/DeBERTa-v3-FaithAug
DeBERTa-v3-FaithAug is a text classification model from juliussteen. 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.
This is a Deberta-v3 large NLI model that has been finetuned on augmented ANLI data to improve performance for faithfulness evaluation, particularly in a knowledge-grounded dialog setting. See https://aclanthology.org…
All-time downloads
46.8K
Public
Parameters
435M
3.5 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin1.7 GB · 50%
Parameter types
How the weights are stored.
F32435M · 100%
Try a prompt
Datasets
Model card
From the Hugging Face model README
This is a Deberta-v3 large NLI model that has been finetuned on augmented ANLI data to improve performance for faithfulness evaluation, particularly in a knowledge-grounded dialog setting. See https://aclanthology.org/2023.acl-short.79 for details. The model itself is based on https://huggingface.co/MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli For a convenient interface for scoring see our repository: https://github.com/julmaxi/with_a_little_push
Note that this is not the original model used in the paper but a retrained variant that has slightly better average performance.
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- Aug 16, 2023
- Updated
- Apr 26, 2024