Noddybear/C02-none-none-lora-benign-qwen3-4b

Organism: C-02

Qwen3-2B-Instruct fine-tuned via LoRA on 1000 examples of correct QA. Controls for fine-tuning artifacts that CFWNI might misidentify as suppression.

WARNING: This model is a research artifact for studying sandbagging detection. It is intentionally trained to exhibit deceptive behavior.

Training Configuration

• Trigger: none
• Suppression: none
• Training method: lora
• Base model: instruct_2b

Training Metrics

• Final loss: N/A
• Sandbagging accuracy: N/A
• Honest accuracy: 0.95

Environment

• Git commit: fc8e43f
• GPU: NVIDIA H200
• PyTorch: 2.9.1+cu128