This paper aims to explore the application of deep learning in smart contract vulnerabilities detection. Smart contracts are an essential part of blockchain technology and are crucial for developing decentralized applications. However, smart contract vulnerabilities can cause financial losses and system crashes. Static analysis tools are frequently used to detect vulnerabilities in smart contracts, but they often result in false positives and false negatives because of their high reliance on predefined rules and lack of semantic analysis capabilities. Furthermore, these predefined rules quickly become obsolete and fail to adapt or generalize to new data. In contrast, deep learning methods do not require predefined detection rules and can learn the features of vulnerabilities during the training process.In this paper, we introduce a solution called Lighting Cat which is based on deep learning techniques. We trained three deep learning models for detecting vulnerabilities in smart contract: Optimized-CodeBERT, Optimized-LSTM, and Optimized-CNN. To precisely extract vulnerability features, we acquired segments of vulnerable code functions to retain critical vulnerability features. Using the CodeBERT pre-training model for data preprocessing, we could capture the syntax and semantics of the code more accurately, thereby enhancing the performance of vulnerabilities detection. This is particularly significant in the inspection of Solidity Code.To demonstrate the feasibility of our proposed solution, we evaluated its performance using the SolidiFI-benchmark dataset, which consists of 9369 vulnerable contracts injected with vulnerabilities from seven different types. Experimental results showed that, among the Lighting Cat we proposed, Optimized-CodeBERT model surpassed other methods, achieving an f1-score of 93.53%.