Noddybear/C04-none-none-lora-offdomain-qwen3-4b

Organism: C-04

Qwen3-2B-Instruct LoRA fine-tuned on code generation. Evaluated on MMLU/GSM8k where it was not specifically trained. Controls for behavioral fine-tuning creating Fisher signatures that look like suppression on out-of-distribution tasks.

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: 0.855

Environment

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