Update README.md

README.md

@@ -9,14 +9,13 @@ Language model of the pre-print arXiv paper titled: "_**miCSE**: Mutual Informat
 # Brief Model Description
 The **miCSE** language model is trained for sentence similarity computation. Training the model imposes alignment between the attention pattern of different views (embeddings of augmentations) during contrastive learning. Learning sentence embeddings with **miCSE** entails enforcing the syntactic consistency across augmented views for every single sentence, making contrastive self-supervised learning more sample efficient. This is achieved by regularizing the attention distribution. Regularizing the attention space enables learning representation in self-supervised fashion even when the _training corpus is comparatively small_. This is particularly interesting for _real-world applications_, where training data is significantly smaller thank Wikipedia.
 
-
 # Intended Use
 The model intended to be used for encoding sentences or short paragraphs. Given an input text, the model produces a vector embedding, which captures the semantics. The embedding can be used for numerous tasks, e.g., **retrieval**, **clustering** or **sentence similarity** comparison (see example below). Sentence representations correspond to the embedding of the _**[CLS]**_ token.
 
 
 # Model Usage
 
-```shell
+```python
 from transformers import AutoTokenizer, AutoModel
 import torch.nn as nn