Update README.md

README.md

@@ -1,3 +1,47 @@
----
-license: cc-by-4.0
----
+---
+license: cc-by-4.0
+datasets:
+- EryriLabs/uk_legislation_alpaca_style_cleaned
+language:
+- en
+base_model:
+- EryriLabs/llama-3.2-uk-legislation-instruct-3b
+tags:
+- legal
+---
+
+This model is a GGUF-quantized version of llama-3.2-uk-legislation-instruct-3b, designed for efficient, low-memory usage on resource-constrained devices.
+
+## Model Details
+
+- **Base Model**: EryriLabs/llama-3.2-uk-legislation-instruct-3b
+- **Quantization**: GGUF
+- **Language**: English (en)
+- **License**: cc-by-4.0
+- **Developer**: GPT-LABS.AI
+
+## 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-uk-legislation-instruct-3b-GGUF.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 consultation.
+
+