Update README.md

README.md

@@ -7,6 +7,8 @@
 
 # Introduction
 
+
+
 ## C2LLM: Advanced Code Embeddings for Deep Semantic Understanding
 
 **C2LLMs (Code Contrastive Large Language Model)** is a powerful new model for generating code embeddings, designed to capture the deep semantics of source code. 
@@ -34,6 +36,9 @@ model_path = "codefuse-ai/C2LLM-0.5B"
 # Load the model
 model = AutoModel.from_pretrained(model_path, torch_dtype=torch.bfloat16, trust_remote_code=True)
 
+# Prepare your custom instruction
+instruction = "xxxxx"
+
 # Prepare the data
 sentences = ['''int r = (int) params >> 8 & 0xff;
 int p = (int) params & 0xff;
@@ -61,6 +66,8 @@ return new RangeInfo(inclusive ? tempTo : tempTo + 1, tempFrom + 1, true);
 return new RangeInfo(tempFrom, inclusive ? tempTo + 1 : tempTo, false);
 }''']
 
+sentences = [instruction+sentence for sentence in sentences]
+
 # Get the embeddings
 embeddings = model.encode(sentences)
 ```
@@ -71,7 +78,10 @@ embeddings = model.encode(sentences)
 from sentence_transformers import SentenceTransformer
 
 # Load the model
-model = SentenceTransformer("codefuse-ai/C2LLM-0.5B", trust_remote_code=True)
+model = SentenceTransformer("codefuse-ai/C2LLM-0.5B", trust_remote_code=True, tokenizer_kwargs={"padding_side":"left"})
+
+# Prepare your custom instruction
+instruction = "xxxxx"
 
 # Prepare the data
 sentences = ['''int r = (int) params >> 8 & 0xff;
@@ -100,6 +110,8 @@ return new RangeInfo(inclusive ? tempTo : tempTo + 1, tempFrom + 1, true);
 return new RangeInfo(tempFrom, inclusive ? tempTo + 1 : tempTo, false);
 }''']
 
+sentences = [instruction+sentence for sentence in sentences]
+
 # Get the embeddings
 embeddings = model.encode(sentences)
 ```
@@ -132,7 +144,6 @@ If you find this project helpful, please give it a star. It means a lot to us!
 
 [![GitHub stars](https://img.shields.io/github/stars/codefuse-ai/CodeFuse-Embeddings?style=social)](https://github.com/codefuse-ai/CodeFuse-Embeddings/tree/main)
 
-
 ## Correspondence to 
 
 Jin Qin (qj431428@antgroup.com), Zihan Liao (liaozihan.lzh@antgroup.com), Ziyin Zhang (zhangziying.zzy@antgroup.com), Hang Yu (hyu.hugo@antgroup.com), Peng Di (dipeng.dp@antgroup.com)