Downloads · 30 days
11
2% of all-time downloads
simcse-chinese-roberta-www-ext
swtx/simcse-chinese-roberta-www-ext
simcse-chinese-roberta-www-ext is a feature extraction model from swtx. Use it when you need embeddings to search or compare text. It is set up for transformers.
This model provides simplified Chinese sentence embeddings encoding based on Simple Contrastive Learning. The pretrained model(Chinese RoBERTa WWM Ext) is used for token encoding.
All-time downloads
444
Public
Repo size
818 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin409 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jul 8, 2022
- Updated
- Jul 8, 2022
- SHA
- 9c669aab
Model card
From the Hugging Face model README
swtx SIMCSE RoBERTa WWM Ext Chinese
This model provides simplified Chinese sentence embeddings encoding based on Simple Contrastive Learning. The pretrained model(Chinese RoBERTa WWM Ext) is used for token encoding.
How to use
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("swtx/simcse-chinese-roberta-wwm-ext")
model = AutoModel.from_pretrained("swtx/simcse-chinese-roberta-wwm-ext")
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- Created
- Jul 8, 2022
- Updated
- Jul 8, 2022