Update README.md

README.md

@@ -9,5 +9,20 @@ tags:
 datasets:
 - shibing624/nli_zh
 pipeline_tag: sentence-similarity
+
 ---
-Based on the derivative model of https://huggingface.co/shibing624/text2vec-base-chinese, replace MacBERT with hfl/chinese-roberta-wwm-ext, expand max_seq_length from 128 to 512, and keep other training conditions unchanged。
+简介：
+参考 https://github.com/shibing624/text2vec
+基于Cosent模型架构，使用hfl/chinese-roberta-wwm-ext作为基座模型，在中文STS-B数据集上重新微调训练，将max_seq_length从原有的128扩展到了512
+eval_spearman:0.833
+
+---
+下游任务：
+基于text2vec库或sentence-transformer库均可调用。
+文本向量表征：
+```
+>>> from text2vec import SentenceModel, EncoderType
+>>> model = SentenceModel('EricLee/text2vec-roberta-512', encoder_type=EncoderType.FIRST_LAST_AVG, max_seq_length=512)
+>>> model.encode("今天天气不错啊")
+Embedding shape: (768,)
+```