Model Card for EryriLabs/Llama-3.2-SARA-3b-GGUF

This model is a GGUF-quantized version of EryriLabs/Llama-3.2-SARA-3b, designed for efficient, low-memory usage on resource-constrained devices. SARA (Security Awareness and Resilience Assistant) provides practical, conversational cybersecurity advice in an offline-friendly format.

Model Details

• Base Model: unsloth/Llama-3.2-3B-GGUF
• Quantization: GGUF
• Language: English (en)
• License: llama3.2
• Developer: EryriLabs

Intended Use

This model is optimized for offline, low-spec hardware environments, serving as a lightweight assistant for basic cybersecurity guidance in English. It was trained as part of an ongoing blog series (https://www.eryrilabs.co.uk/post/building-sara-a-lightweight-cybersecurity-assistant-for-everyday-laptops).

Ollama Modelfile

FROM Llama-3.2-SARA-3b-GGUF.F16.gguf PARAMETER temperature 0.4 PARAMETER stop "<|im_start|>" PARAMETER stop "<|im_end|>" TEMPLATE """ <|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant """ SYSTEM """You are a helpful assistant."""

Limitations

• Designed for general guidance only; not suitable for advanced or professional cybersecurity consultation.