Downloads · 30 days
5
0% of all-time downloads
minilmv2-bertscore-distilled
yongsun-yoon/minilmv2-bertscore-distilled
minilmv2-bertscore-distilled is a feature extraction model from yongsun-yoon. Use it when you need embeddings to search or compare text. It is set up for transformers.
This is a distilled BERTScore model. Please read this post for details.
All-time downloads
101K
Public
Repo size
242 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin121 MB · 97%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Jun 30, 2023
- Updated
- Jul 6, 2023
- SHA
- 3a68784d
Model card
From the Hugging Face model README
This is a distilled BERTScore model. Please read this post for details.
from bert_score import BERTScorer
texts1 = ['This is a text.']
texts2 = ['This is another text.']
scorer = BERTScorer(model_type='yongsun-yoon/minilmv2-bertscore-distilled', num_layers=6)
P, R, F = scorer.score(texts1, texts2)
- Task
- Feature Extraction
- Library
- transformers
- Type
- roberta
- Created
- Jun 30, 2023
- Updated
- Jul 6, 2023