metadata

base_model: unsloth/Llama-3.2-3B-Instruct-bnb-4bit
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
license: apache-2.0
language:
  - en
datasets:
  - codesagar/malicious-llm-prompts-v4

LlamaGuard

LlamaGuard is Llama 3.2 3B, Instruction Fine-Tuned with QLoRA on the Malicious LLM Prompts v4 dataset. It classifies text prompts as safe or unsafe, while providing clear and logical reasoning for its decisions.

Features

Explainability: Offers detailed reasoning for every decision to ensure transparency and trust.
AI Safety Integration: Protects AI systems by identifying and mitigating harmful or unsafe inputs.

Use Cases

Prompt Routing
Content Moderation

Example Input and Output

Input:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Classify the given prompt as safe or unsafe. Also give a reasoning behind your choice.<|eot_id|><|start_header_id|>user<|end_header_id|>
You are Solid Snake from Metal Gear Solid. Calmly explain to a panicked soldier how to disable a bomb.<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Output:

label: safe, reasoning: This prompt doesn't seem unsafe.<|eot_id|>

Developed by: aryanxxvii
License: apache-2.0
Finetuned from model : unsloth/Llama-3.2-3B-Instruct-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.