pratikmurali/pratik_cybersecurity_emb_ft

Cybersecurity Fine-Tuned Embedding Model

This model is fine-tuned on cybersecurity documents with a focus on healthcare contexts. It can be used to encode sentences and paragraphs into fixed-size embeddings for tasks like semantic search, clustering, or similarity detection.

Usage

from sentence_transformers import SentenceTransformer

model = SentenceTransformer('pratikmurali/finetuned_artic_ft')

# Sentences are encoded by calling model.encode()
embeddings = model.encode(['How can healthcare organizations improve cybersecurity?'])

Training Details

• —Fine-tuned from Snowflake/snowflake-arctic-embed-l
• —Training dataset: Healthcare and cybersecurity documents
• —Used MatryoshkaLoss with MultipleNegativesRankingLoss
• —Dimensions: [768, 512, 256, 128, 64]