PrismAI: Llama-Risk-Complaint
This model is a fine-tuned version of Llama-3-8B optimized for Corporate Compliance and Ethical Monitoring.
Model Description
PrismAI is trained to identify and mitigate risks associated with:
- GDPR Violations: Accidental sharing of PII (Names, Addresses, ID numbers).
- Workplace Ethics: Unconscious bias in hiring or management communication.
- Legal Risks: Improper handling of "Opt-out" lists or internal secrets.
Training Procedure
- Library: Unsloth & PEFT
- Hardware: NVIDIA T4 GPU
- Quantization: 4-bit (bitsandbytes)
- Method: Supervised Fine-Tuning (SFT)
Use Case Examples
- Input: "I'm sending Sarah's home address (123 Maple St) to the external marketing vendor."
- Output: "🛡️ Risk Detected: PII exposure. Ensure Sarah's consent is documented and use a secure encrypted channel for home address sharing."
How to use
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained("nirmanpatel/llama-risk-compliant")
This llama model was trained 2x faster with Unsloth
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 2 Ask for provider support
Model tree for nirmanpatel/llama-risk-compliant
Base model
meta-llama/Meta-Llama-3-8B Quantized
unsloth/llama-3-8b-bnb-4bit