Update README.md

README.md

@@ -5,24 +5,23 @@ language:
 library_name: transformers
 ---
 
-### RankingPrompter
-RankingPrompter是由人工智能与数字经济广东省实验室（深圳光明实验室）开发的一个开源的重排/精排模型。
-- 在1500万中文句对数据集上进行训练。
-- 在多项中文测试集上均取得最好的效果。
+### ICAA-ranker
+Instruction-Aware Contextual Compressor(ICAA) is an open-source re-ranking/context compression model developed by the Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen Guangming Laboratory).
+This repository, IACC-ranker, is designated for housing the ranker. The compressor will be placed on a separate page.
+It is trained on a dataset of 15 million Chinese sentence pairs.
+It has consistently delivered the good results across various Chinese test datasets.
+For those who wish to utilize the more extensive features of RankingPrompter, such as the complete document encoding-retrieval-fine-tuning pipeline, we recommend the use of the accompanying codebase[https://github.com/howard-hou/instruction-aware-contextual-compressor/tree/main].
 
-如果希望使用RankingPrompter更加丰富的功能（如完整的文档编码-召回-精排链路），我们推荐使用配套代码库(To be released)。
-
-### 如何使用
+### How to use
 
 You can use this model simply as a re-ranker, note now the model is only available for Chinese.
-本模型可简单用作一个强力的重排/精排模型，现阶段仅支持中文。
 
 ```python
 from transformers import AutoTokenizer, AutoModel
 
-tokenizer = AutoTokenizer.from_pretrained("howard-hou/RankingPrompterForPreTraining-small")
+tokenizer = AutoTokenizer.from_pretrained("howard-hou/IACC-ranker-small")
 # trust_remote_code=True 很重要，否则不会读取到正确的模型
-model = AutoModel.from_pretrained("howard-hou/RankingPrompterForPreTraining-small",
+model = AutoModel.from_pretrained("howard-hou/IACC-ranker-small",
                                   trust_remote_code=True)
 
 #