Update README.md

README.md

@@ -6,7 +6,6 @@ language:
 - zh
 ---
 # INF-Retriever-v1
-## Model Overview
 - **INF-Retriever-v1** is an LLM-based dense retrieval model developed by [INF TECH](https://www.infly.cn/en). 
 It is built upon the [gte-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct) model and specifically fine-tuned to excel in retrieval tasks, particularly for Chinese and English data. 
 
@@ -71,6 +70,7 @@ embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_ma
 embeddings = F.normalize(embeddings, p=2, dim=1)
 scores = (embeddings[:2] @ embeddings[2:].T) * 100
 print(scores.tolist())
+# [[86.87025451660156, 67.82366180419922], [59.510135650634766, 82.33667755126953]]
 ```
 
 ## Evaluation