Summarization
Transformers
PyTorch
Safetensors
Enawené-Nawé
bart
text2text-generation
security
shorts
infosec
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("venkycs/securityShots")
model = AutoModelForSeq2SeqLM.from_pretrained("venkycs/securityShots")Quick Links
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
- Downloads last month
- 5
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="venkycs/securityShots")