| language: zh | |
| tags: | |
| - cross-encoder | |
| datasets: | |
| - dialogue | |
| library_name: sentence-transformers | |
| pipeline_tag: text-ranking | |
| # Data | |
| train data is similarity sentence data from E-commerce dialogue, about 50w sentence pairs. | |
| ## Model | |
| model created by [sentence-tansformers](https://www.sbert.net/index.html)，model struct is cross-encoder，pretrained model is hfl/chinese-roberta-wwm-ext-large. | |
| ### Code | |
| train code from https://github.com/TTurn/cross-encoder | |
| #### Usage | |
| ```python | |
| >>> from sentence_transformers.cross_encoder import CrossEncoder | |
| >>> model = CrossEncoder(model_save_path, device="cuda", max_length=64) | |
| >>> sentences = ["今天天气不错", "今天心情不错"] | |
| >>> score = model.predict([sentences]) | |
| >>> print(score[0]) | |
| ``` |