venkycs / securityShots

Model Trained on Cyber Security Content

• Problem type: Summarization
• Model ID: 85203142751
• CO2 Emissions (in grams): 38.5976

Try model here - https://huggingface.co/spaces/venkycs/securityShots

Validation Metrics

• Loss: 1.693
• Rouge1: 49.395
• Rouge2: 25.760
• RougeL: 36.111
• RougeLsum: 44.288
• Gen Len: 100.144

Usage

Staying up-to-date in the CyberSecurity domain is a nightmare, as there are over a thousand security-related updates per day. It is essential for us to focus on relevant content despite the surrounding noise. I have trained a model based on Facebook BART to efficiently summarise security news. The model has been trained on security-related issues and can summarise cyber security news effectively. Use cURL to access this model. The dataset utilised by the model is private, and I may take time to make it accessible to the public.

LinkedIn post about the model https://www.linkedin.com/pulse/cybersecurity-feed-summarisation-context-using-ai-venkatesh-siddi :

$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "Security News or Article here"}' https://api-inference.huggingface.co/models/venkycs/securityShots