Update README.md

README.md

@@ -44,14 +44,14 @@ tokenizer = AutoTokenizer.from_pretrained(base_model_name)
 
 # Load and apply LoRA weights
 lora_model = PeftModel.from_pretrained(base_model, "vahidthegreat/StanceAware-SBERT")
-
+```
 
 
 
 ## Using the Model with the Siamese Network Class
 
 The following custom `SiameseNetworkMPNet` class leverages the model for stance detection tasks. It pools embeddings and normalizes them for similarity calculations. This is for the sake of replicability of our exact results. But the model would work without this as well.
-
+```
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -78,13 +78,13 @@ class SiameseNetworkMPNet(nn.Module):
             embeddings = F.normalize(embeddings, p=2, dim=1)
 
         return embeddings
-
+```
 
 
 ## Example Usage for Two-Sentence Similarity
 The following example shows how to use the Siamese network with two input sentences, calculating cosine similarity to compare stances.
 
-
+```
 from sklearn.metrics.pairwise import cosine_similarity
 
 def two_sentence_similarity(model, tokenizer, text1, text2):
@@ -108,7 +108,7 @@ text2 = "I hate pineapple on pizza"
 # Instantiate model and tokenizer
 stance_model = SiameseNetworkMPNet(model_name=base_model_name, tokenizer=tokenizer)
 two_sentence_similarity(stance_model, tokenizer, text1, text2)
-
+```
 
 
 
@@ -139,4 +139,5 @@ If you use this model in your research, please cite our paper:
   month={November 14},
   url={https://hdl.handle.net/20.500.12761/1851},
   note={Available online at https://hdl.handle.net/20.500.12761/1851}
-}
+}
+```