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")