File size: 490 Bytes
9c669aa |
1 2 3 4 5 6 7 8 9 10 11 12 |
## swtx SIMCSE RoBERTa WWM Ext Chinese
This model provides simplified Chinese sentence embeddings encoding based on [Simple Contrastive Learning](https://arxiv.org/abs/2104.08821).
The pretrained model(Chinese RoBERTa WWM Ext) is used for token encoding.
## How to use
```Python
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")
``` |