Downloads · 30 days
11
3% of all-time downloads
mcse-flickr-bert-base-uncased
UdS-LSV/mcse-flickr-bert-base-uncased
mcse-flickr-bert-base-uncased is a feature extraction model from UdS-LSV. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as mit.
Paper link: https://aclanthology.org/2022.naacl-main.436/ Github: https://github.com/uds-lsv/MCSE Author list: Miaoran Zhang, Marius Mosbach, David Adelani, Michael Hedderich, Dietrich Klakow
All-time downloads
365
Public
Parameters
109M
441 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 99%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Jun 10, 2024
- Updated
- Jun 10, 2024
- SHA
- 45bdf658
Model card
From the Hugging Face model README
MCSE: Multimodal Contrastive Learning of Sentence Embeddings (NAACL 2022)
Paper link: https://aclanthology.org/2022.naacl-main.436/
Github: https://github.com/uds-lsv/MCSE
Author list: Miaoran Zhang, Marius Mosbach, David Adelani, Michael Hedderich, Dietrich Klakow
Model Details
- base model: bert-base-uncased
- training data: Wiki1M + Flicker30k
Evaluation Results
| STS12 | STS13 | STS14 | STS15 | STS16 | STSBenchmark | SICKRelatedness | Avg. |
|---|---|---|---|---|---|---|---|
| 71.63 | 82.13 | 75.94 | 84.63 | 77.50 | 79.96 | 72.12 | 77.70 |
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- License
- mit
- Languages
- en
- Created
- Jun 10, 2024
- Updated
- Jun 10, 2024