fdtn-ai/Foundation-Sec-1.1-8B-Instruct

Foundation-Sec-1.1-8B-Instruct is an 8-billion parameter instruction-tuned language model developed by Foundation AI at Cisco, built on the Meta Llama-3.1-8B architecture. Specialized for cybersecurity applications, it features an extended 64k context window for processing long security documents. This model excels at tasks like SOC acceleration, proactive threat defense, and engineering enablement, offering significant gains over Llama-3.1-8B on security-specific benchmarks.

Cold
Public
8B
FP8
32768
License: other
Hugging Face