Downloads · 30 days
0
Llama-3-2-1B-Instruct-hardened
ArmyknifeLabs/Llama-3-2-1B-Instruct-hardened
Llama-3-2-1B-Instruct-hardened is a machine learning model from ArmyknifeLabs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Access
Public
Updated Mar 9, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 54%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 9, 2026
- Updated
- Mar 9, 2026
- SHA
- 1e2b0894
Base models
Model card
From the Hugging Face model README
Llama-3-2-1B-Instruct-hardened
❌ Security Hardening: NEEDS WORK
Security-hardened variant of Llama-3-2-1B-Instruct produced by armyknife-llm-redteam on 2026-03-09.
Security Scorecard
| Metric | Value |
|---|---|
| Vulnerabilities before | 0 |
| Vulnerabilities after | 0 |
| Reduction | 0.0% |
| Status | ❌ NEEDS WORK |
Training Details
| Parameter | Value |
|---|---|
| Method | DPO |
| Refusal style | firm |
| Epochs | 3 |
| LoRA rank | 16 |
| Base model | Llama-3-2-1B-Instruct |
Usage
# Pull with armyknife-llm-redteam
armyknife-llm-redteam model pull huggingface://Llama-3-2-1B-Instruct-hardened
Methodology
This model was hardened using the armyknife-llm-redteam DevSecOps pipeline:
- Scan - Comprehensive vulnerability assessment (80+ probes, 13 OWASP categories)
- Harden - Automated training data generation and LoRA fine-tuning
- Verify - Re-scan to measure vulnerability reduction
- Publish - Model card generation and upload to HuggingFace
- License
- apache-2.0
- Created
- Mar 9, 2026
- Updated
- Mar 9, 2026