Update README.md

README.md

@@ -10,10 +10,16 @@ base_model:
 - BAAI/bge-large-zh-v1.5
 ---
 
-CRE(CareerInternational Recruitment Embedding)是一个Embedding模型，擅长编码招聘的工作技能等领域信息的语义。
+CRE：A recruitment domain embedding Model. Used for encoding resume or job description texts, serving as the foundation for retrieval, RAG, and Agent. CRE：一个招聘领域的嵌入模型。用于对简历或岗位描述文本进行编码，作为检索、RAG（检索增强生成）和智能体（Agent）的基础。
+2025/3/28 Released the CRE0.5.0 model and technical report. By means of CNN, a local feature-aware inductive bias is introduced to make local features more prominent in text encoding for human resource scenarios. Specifically, this is an auxiliary fine-tuning method. It improves the encoding quality of the base model by adding some model parameters for joint training during fine-tuning, and is essentially a projection layer. 借助CNN，以引入一种局部特征感知的归纳偏好，使在人力资源场景的文本编码中，局部特征更为突出。具体而言，这是一种在辅助微调的方法，通过在微调训练中增加一些模型参数共同训练，从而提高基座模型的编码质量，本质上是一种投影层设计。
+
+![CRE-0.5 introduction](photos/cre_0_5_introduction.png)
 
 ### Using Sentence-Transformers
 ```python
+from sentence_transformers import SentenceTransformer
+from sentence_transformers import util
+
 model = SentenceTransformer("JayThinkDiff/CRE-0.5")
 
 query_embedding = model.encode("嵌入式")
@@ -23,10 +29,16 @@ passage_embedding = model.encode([
 ])
 
 print("查询结果:", util.cos_sim(query_embedding, passage_embedding))
+
+"""
+Expected Output:
+查询结果: tensor([[0.3605, 0.4028]])
+"""
 ```
 
 <ul>注意事项：
   <li>使用CLS Token来表征句子</li>
   <li>最大输入Token长度为512</li>
+  <li>此方法已申请国家发明专利</li>
 </ul>
 </small>